ac.tandem/docs-mcp - MCP Verify

← Back to search

Search • Sprawl Radar • TrustOps • Gateway • Ledger • Mandates • Hosting • Agent Commerce • Docs Compiler • Demo • Trust Index • Discovery Sources • Submit Repo • GitHub Action • Plans • Intelligence API • Verified Profiles • Shortlists • Rankings • Compare • Badges • Claim • ChatGPT compatible • Claude compatible • Healthcare • Digests • RSS • RSS XML • Backfill • MCP API

ac.tandem/docs-mcp

Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.

JSON report • Policy • Badge metadata • History API • • Global feed

Decision: Allow with approval

Why: exec-capable tools + no confirmation safeguards + high-risk tools need review

Next: export policy, require approval for writes, add authenticated validation

EXECUTIVE VERDICT

Executive verdict

Production trust decision: Allow with approval

Reason: exec-capable tools + no confirmation safeguards + high-risk tools need review

Next action: export policy, require approval for writes, add authenticated validation

Production decision

Allow with approval

exec-capable tools + no confirmation safeguards + high-risk tools need review

Current score

70.4

Snapshot trustsnap_69fee57bf5cd1ad8

Next action

export policy, require approval for writes, add authenticated validation

Claim the profile to add evidence, trigger validation, and configure monitoring.

Compare alternatives Export policy Open report JSON

Observed Attention

High observed attention

AI discovery detected. This MCP server has recently appeared in AI-assisted discovery or evaluation traffic on Verify.

Machine trust evaluator activity
Possible agent/script activity
profile / compare / compare API / policy / ledger inspection

Bucketed signal based on recent segmented Verify telemetry. Crawler and evaluator activity is not treated as confirmed human demand.

Claim this profile to control the metadata agents are reading and publish verified ownership, security contact, policy metadata, badge status, and Intelligence API fields.

Evidence Tool risk Compatibility Policy History Badge Raw report

Status

Healthy

Score

70.4

Transport

streamable-http

Tools

Current trust snapshot

Snapshot ID

trustsnap_69fee57bf5cd1ad8

Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.

Snapshot generated

Jul 31, 2026 07:00:21 AM UTC

All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.

Last validated

Jul 31, 2026 05:33:13 AM UTC

Age: 1.45h • freshness band: Verified in last 24h • display score: 70.41

Production trust decision

Allow with approval

exec-capable tools + no confirmation safeguards + high-risk tools need review

Readiness class

Safe for evaluation

The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.

Canonical machine links

Compare index

/compare.json

Compare API

/v1/compare?server=ac.tandem%2Fdocs-mcp

Trust summary

/v1/servers/ac.tandem/docs-mcp/trust-summary

Report JSON

/v1/servers/ac.tandem/docs-mcp/report

Policy export

/v1/servers/ac.tandem/docs-mcp/policy

Badge metadata

/v1/servers/ac.tandem/docs-mcp/badge

Ledger evidence

/v1/servers/ac.tandem/docs-mcp/ledger

Human compare URL

/compare?server=ac.tandem%2Fdocs-mcp

SERVER OWNER FUNNEL

Own this MCP?

Claim ownership, prove control with a GitHub, DNS, HTTP, MCP metadata, or email-domain challenge, revalidate now, publish a badge, configure monitoring, and unlock a verified server profile.

1. Claim

unclaimed

with GitHub, DNS, or HTTP challenge instructions.

2. Revalidate

POST /v1/servers/ac.tandem/docs-mcp/revalidate

Verified owners get priority queueing after proof succeeds.

3. Badge

Verified by MCP Verify - score 70.4 - last checked Jul 31, 2026

4. Monitor

Continuous Verify plan is self-serve: choose a tier, configure watches, add authenticated validation, trigger revalidation, and use the badge.

Paid profile

Verified Server Profile

Add verified publisher identity, security metadata, evidence packs, badge customization, and owner analytics without buying a better score.

Badge embed

[![Verified by MCP Verify](https://verify.sentinelsignal.io/badge/ac.tandem/docs-mcp.svg)](https://verify.sentinelsignal.io/servers/ac.tandem/docs-mcp)

MCP TrustOps

TrustOps turns this report into operational controls: freshness SLAs, authenticated validation, semantic benchmarks, policy exports, alert subscriptions, badges, cost/compliance metadata, and runtime routing. Fresh trusted index decisions stay separate from long-tail inventory so stale scores do not masquerade as current evidence.

Freshness band

Verified in last 24h

Policy SLA: 168.0h • confidence-weighted score: 53.7 • stale score suppressed: ✕

Policy exports

Export policy

Formats: json, rego, yaml, github_action, gateway_config, client_report

Runtime routing

/v1/decide

Returns allowed tools, blocked tools, approval requirement, and reason.

Hosted runtime

Verify Hosted MCP

Deploy trusted servers from GitHub with secrets, egress controls, releases, rollback, and audit events.

Authenticated validation

Premium publisher feature: paid authenticated runs verify scopes, write-action safeguards, and authorized tool execution.

Active trust badges

Freshly Validated Claude Remote MCP Compatible No Critical Risk

Semantic benchmarks

available

Templates cover GitHub, database, healthcare, web search, and CRM least-privilege jobs.

Supply chain

metadata signal

Deep scan checks are marked separately from public metadata signals.

Compliance metadata

Terms, privacy, SOC 2, HIPAA, GDPR, retention, deletion, and audit-log fields are tracked as enterprise metadata.

Alert subscription types

Status changes Score drops or recovers Freshness SLA breach Validation schema drift OAuth or auth behavior changes Tool surface changes New or changed write tool Supply-chain signal changes Legal or compliance metadata changes

MCP Runtime hosting

Verify Hosted MCP turns a trusted server report into a managed remote MCP endpoint with GitHub deployment provenance, sandbox policy, encrypted secrets, release history, rollback, and audit/usage events.

Activation readiness

✓

Trusted hosted runtimes require fresh validation, a passing server state, a remote endpoint, and a minimum score.

Minimum tier

TrustOps

Publisher claim plus paid TrustOps tier are required before secrets or releases can be created.

Hosted endpoint

/hosted/{namespace}/{name}/mcp

The endpoint enforces egress allowlists and records audit/usage events.

Blockers

none

Deployment	Status	Endpoint	Release
No hosted runtime deployments yet.

Production readiness class

Safe for evaluation

The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.

Critical alerts

Production verdicts degrade quickly when critical alerts are active.

Evidence confidence

Confidence score

76.2

Based on 1 recent validations, 26 captured checks, and validation age of 1.5 hours.

Live checks captured

More direct checks increase trust in the current verdict.

Validation age

1.4h

Lower age means fresher evidence.

Recommended for

Claude Desktop

Claude Desktop is marked compatible with score 83.

Smithery

Smithery is marked compatible with score 80.

Generic Streamable HTTP

Generic Streamable HTTP is marked compatible with score 100.

Client compatibility verdicts

Client compatibility only means the server shape can work with a client. Production trust decision and write-action publishing are evaluated separately so a client-compatible server can still be blocked for production.

Client compatibility: ChatGPT

Partially client-compatible

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.

Confidence: high (76.25)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error
step_up_auth_probe • Missing
connector_replay_probe • Missing — Frozen tool snapshots must survive refresh.
request_association_probe • Missing — Roots, sampling, and elicitation should stay request-scoped.

Client compatibility: Claude

Client-compatible

Transport behavior should match Claude-compatible HTTP expectations.

Confidence: high (76.25)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error

Write-action publishing

Publishing blocked

Blocked until safeguards and confirmation semantics are verified for write, exec, or destructive tools.

Confidence: high (76.25)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history

Disagreements: none

action_safety_probe • Error

Snapshot churn risk

Low

No material tool-surface churn detected in the latest comparison.

Confidence: high (76.25)

Evidence provenance

Winner: history

Supporting sources: history, live_validation

Disagreements: none

tool_snapshot_probe • Missing
connector_replay_probe • Missing

Why compatibility is limited by client

ChatGPT custom connector

Partially client-compatible

Remediation checklist

OpenAI connectors expect OAuth for remote server auth.
Dynamic client registration materially improves connector setup.
Transport compliance should be in good shape.
search fetch only is not yet satisfied
oauth configured is not yet satisfied
admin refresh required is not yet satisfied

Claude remote MCP

Client-compatible

Remediation checklist

Transport behavior should match Claude-compatible HTTP expectations.
search fetch only is not yet satisfied
oauth configured is not yet satisfied
admin refresh required is not yet satisfied
safe for company knowledge is not yet satisfied
safe for messages api remote mcp is not yet satisfied

Write-safe publishing

Blocked

Remediation checklist

Add a clearer auth boundary around risky write actions.
Add confirmation or dry-run semantics for risky actions.
Constrain or sandbox exec-capable tools before publishing broadly.

Verdict traces

Production verdict

Safe for evaluation

The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.

Confidence: high (76.25)

Winning source: live_validation

Triggering alerts

No active alert triggers.

Client verdict trace table

Verdict	Status	Checks	Winning source	Conflicts
`openai_connectors`	Partially client-compatible	initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe	live_validation	none
`claude_desktop`	Client-compatible	initialize, tools_list, transport_compliance_probe	live_validation	none
`unsafe_for_write_actions`	Publishing blocked	action_safety_probe	live_validation	none
`snapshot_churn_risk`	Low	tool_snapshot_probe, connector_replay_probe	history	none

Publishability policy profiles

ChatGPT custom connector compatibility

Compatible with review

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: No
Admin Refresh Required: No
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Claude remote MCP compatibility

Connector-compatible

Transport behavior should match Claude-compatible HTTP expectations. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: No
Admin Refresh Required: No
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Compatibility fixtures

ChatGPT custom connector fixture

Degraded

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.

remote_http_endpoint: Passes
oauth_discovery: Degraded
frozen_tool_snapshot_refresh: Passes
request_association: Passes

Anthropic remote MCP fixture

Degraded

Transport behavior should match Claude-compatible HTTP expectations.

remote_transport: Passes
tool_discovery: Passes
auth_connect: Passes
safe_write_review: Degraded

Authenticated validation sessions

Public validation is free. Authenticated validation is paid and proves scoped behavior, write-action safeguards, and authenticated tool execution.

Latest profile

remote_mcp

Authenticated session used

Public score isolation

✓

Preview endpoint

/v1/verify

CI preview endpoint

/v1/ci/preview

Public server reputation

Validation success 7d

1.0

Validation success 30d

1.0

Mean time to recover

n/a

Breaking diffs 30d

Registry drift frequency 30d

Snapshot changes 30d

Incident & change feed

Timestamp	Event	Details
Jul 31, 2026 05:33:13 AM UTC	Latest validation: healthy	Score 70.4 with status healthy.

Capabilities

OAuth: ✕
DCR/CIMD: ✕
Prompts: ✓
Homepage: https://tandem.ac/docs-mcp
Docs: none
Support: none
Icon: none
Remote endpoint: https://tandem.ac/mcp
Server card: none

Use-case taxonomy

development search web cloud

Security posture

Tools analyzed

High-risk tools

Destructive tools

Exec tools

Egress tools

Secret tools

Bulk-access tools

Risk distribution

low:7, medium:5, high:1

Agent Commerce & Payment Readiness - Beta

Beta assessment. Verify separates commerce-adjacent context from observed payment execution. Usage, billing, pricing, card, wallet, or meter terms alone do not make a server payment-capable. This is not a certification of safety, compliance, or fraud prevention.

Overall

None

Auth posture

Payment readiness

Delegation safety

Tool risk

Commerce signal: weak Payment capable: none Payment execution: no Billing/usage context: no Quote/pricing context: no Numeric price context: yes Commercial quote context: no Checkout/charge signal: no Checkout term observed: no Human confirmation: unknown Spending policy: yes Receipt support: unknown Auth required: no Operator identity: declared Tool risk: administrative Delegation level: none

Detected payment rails

none detected

Purchase stages

none detected

Evidence level

inferred

Confidence

low

Warnings

No commerce-specific warnings generated.

Evidence

Field	Value	Source	Matched terms	Confidence
commerce_signal	weak	tool_schema	limit, rate	low

Recommended operator fixes

No commerce-specific fixes suggested.

Tool capability & risk inventory

Tool	Capabilities	Risk	Findings	Notes
`search_docs`	read exec admin export	High	command execution bulk data access freeform input surface	No explicit safeguard hints detected.
`get_doc`	read network filesystem	Medium	freeform input surface	No explicit safeguard hints detected.
`get_start_path`	read filesystem admin	Medium	none	No explicit safeguard hints detected.
`recommend_next_docs`	read filesystem admin export	Medium	bulk data access freeform input surface	No explicit safeguard hints detected.
`answer_how_to`	admin export	Medium	bulk data access	No explicit safeguard hints detected.
`get_tandem_guide`	read	Low	none	No explicit safeguard hints detected.
`warmup_docs_cache`	read	Low	none	No explicit safeguard hints detected.
`get_docs_cache_status`	read	Low	none	No explicit safeguard hints detected.
`refresh_docs_index`	other	Low	none	No explicit safeguard hints detected.
`refresh_doc_page`	filesystem	Low	freeform input surface	No explicit safeguard hints detected.
`invalidate_docs_cache`	read network filesystem	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.
`compare_docs_index_refresh`	other	Low	none	No explicit safeguard hints detected.
`compare_doc_page_refresh`	filesystem	Low	freeform input surface	No explicit safeguard hints detected.

Write-action governance

Governance status

Error

Safe to publish

Auth boundary

public_or_unclear

Blast radius

High

High-risk tools

Confirmation signals

none

Safeguard count

Status detail: 1 high-risk tool(s), 1 exec-capable tool(s) are exposed without a clear auth boundary; no safeguards or confirmation signals detected.

Tool	Risk	Flags	Safeguards
`search_docs`	High	command execution bulk data access freeform input surface	no

Action-controls diff

Snapshot changed

Disabled-by-default candidates

none

Manual review candidates

none

New actions

Action	Risk	Flags
No newly added actions.

Changed actions

Action	Change types	Risk
No materially changed actions.

Why this score?

Access & Protocol

31/44

Connectivity, auth, and transport expectations for common clients.

Interface Quality

35/56

How well the tool/resource interface communicates and behaves under automation.

Security Posture

26.75/36

How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.

Reliability & Trust

17.75/24

Operational stability, consistency, and trustworthiness over time.

Discovery & Governance

21.5/28

How well the server is documented, listed, and governed in public registries.

Adoption & Market

6/8

Adoption clues and public evidence that the server is intended for external use.

Algorithmic score breakdown

Auth Operability

2/4

Measures whether auth discovery and protected access behave predictably for clients.

Error Contract Quality

0/4

Grades machine-readable error structure, status alignment, and remediation hints.

Rate-Limit Semantics

2/4

Checks whether quota/throttle responses are deterministic and automation-friendly.

Schema Completeness

3/4

Completeness of tool descriptions, parameter docs, examples, and schema shape.

Backward Compatibility

2/4

Stability score across tool schema/name drift relative to prior validations.

SLO Health

3/4

Availability, latency, and burst-failure profile across recent validation history.

Security Hygiene

4/4

HTTPS posture, endpoint hygiene, and response-surface hardening checks.

Task Success

4/4

Can an agent reliably initialize, enumerate tools, and execute core MCP flows?

Trust Confidence

1.8/4

Confidence-adjusted reliability score that penalizes low evidence volume.

Abuse/Noise Resilience

4/4

How well the server preserves core behavior in the presence of noisy traffic patterns.

Prompt Contract

2/4

Quality of prompt metadata, argument shape, and prompt discoverability for clients.

Resource Contract

4/4

How completely resources and resource templates describe URIs, types, and usage shape.

Discovery Metadata

4/4

Homepage, docs, icon, repository, support, and license coverage for directory consumers.

Registry Consistency

2/4

Agreement between stored registry metadata, live server-card data, and current validation output.

Installability

4/4

How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.

Session Semantics

4/4

Determinism and state behavior across repeated MCP calls, including sticky-session surprises.

Tool Surface Design

3/4

Naming clarity, schema ergonomics, and parameter complexity across the tool surface.

Result Shape Stability

2/4

Stability of declared output schemas across validations, with penalties for drift or missing shapes.

OAuth Interop

3/4

Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.

Recovery Semantics

0/4

Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.

Maintenance Signal

3/4

Versioning, update recency, and historical validation cadence that indicate active stewardship.

Adoption Signal

3/4

Directory presence and distribution clues that suggest the server is intended for external use.

Freshness Confidence

3/4

Confidence that recent validations are current enough and dense enough to trust operationally.

Transport Fidelity

4/4

Whether declared transport metadata matches the observed endpoint behavior and response formats.

Spec Recency

3/4

How close the server’s claimed MCP protocol version is to the latest known public revision.

Session Resume

3/4

Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.

Step-Up Auth

3/4

Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.

Transport Compliance

0/4

Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.

Utility Coverage

2/4

Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.

Advanced Capability Coverage

3/4

Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.

Connector Publishability

3/4

How ready the server looks for client catalogs and managed connector programs.

Tool Snapshot Churn

3/4

Stability of the tool surface across recent validations, including add/remove and output-shape drift.

Connector Replay

3/4

Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.

Request Association

3/4

Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.

Interactive Flow Safety

3/4

Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.

Action Safety

2/4

Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.

Official Registry Presence

4/4

Whether the server appears directly or indirectly in the official MCP registry.

Provenance Divergence

4/4

How closely official registry metadata, the live server card, and public repo/package signals agree with each other.

Safety Transparency

2/4

Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.

Tool Capability Clarity

4/4

How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.

Destructive Operation Safety

3/4

Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.

Egress / SSRF Resilience

2/4

Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.

Execution / Sandbox Safety

3.8/4

Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.

Data Exfiltration Resilience

3/4

Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.

Least Privilege Scope

2/4

Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.

Secret Handling Hygiene

3/4

Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.

Supply Chain Signal

2.5/4

Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.

Input Sanitization Safety

3/4

Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.

Tool Namespace Clarity

4/4

Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.

Compatibility profiles

OpenAI Connectors

66.7

partial

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.

Connector URL: https://tandem.ac/mcp
# No OAuth metadata detected.
# Server: ac.tandem/docs-mcp

Claude Desktop

83.3

compatible

Transport behavior should match Claude-compatible HTTP expectations.

{
  "mcpServers": {
    "docs-mcp": {
      "command": "npx",
      "args": ["mcp-remote", "https://tandem.ac/mcp"]
    }
  }
}

Smithery

80.0

compatible

Machine-readable failure semantics should be present.

smithery mcp add "https://tandem.ac/mcp"

Generic Streamable HTTP

100.0

compatible

No major blockers detected.

curl -sS https://tandem.ac/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Actionable remediation

Severity	Remediation	Why it matters	Recommended action
High	Add confirmation and dry-run semantics for risky actions	High-risk write, delete, exec, or egress tools should communicate safeguards clearly.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
High	Align session and protocol behavior with Streamable HTTP expectations	Clients increasingly rely on MCP-Protocol-Version, session teardown, and expired-session semantics.	Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec. Playbook Return `Mcp-Session-Id` and `Mcp-Protocol-Version` headers consistently on streamable HTTP responses. Honor `DELETE` session teardown and return `404` when a deleted session is reused. Reject invalid protocol-version headers with `400 Bad Request`.
High	Associate roots, sampling, and elicitation with active client requests	Modern MCP guidance expects roots, sampling, and elicitation traffic to be tied to an active client request instead of arriving unsolicited on idle sessions.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
High	Expose /.well-known/oauth-protected-resource	Without a protected-resource document, OAuth clients cannot discover auth requirements reliably.	Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata. Playbook Serve `/.well-known/oauth-protected-resource` from the same host as the MCP endpoint. Point it at the authorization server metadata URL. Confirm clients receive consistent auth hints before tool execution.
High	Keep connector refreshes backward compatible	Managed connector clients freeze tool snapshots, so removed tools, new required args, and breaking output changes can break published integrations after refresh.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
High	Publish OAuth authorization-server metadata	Clients need authorization-server metadata to discover issuer, endpoints, and DCR support.	Publish /.well-known/oauth-authorization-server from your issuer and include registration_endpoint when supported. Playbook Publish `/.well-known/oauth-authorization-server` from the issuer. Add `registration_endpoint` if DCR is supported. Verify issuer, authorization, token, and jwks metadata are all reachable.
High	Publish a complete server card	Missing or incomplete server-card metadata weakens discovery, documentation, and trust signals.	Serve /.well-known/mcp/server-card.json and include tools, prompts/resources, homepage, and support links. Playbook Publish `/.well-known/mcp/server-card.json`. Include homepage, repository, support, tools, prompts/resources, and auth metadata. Revalidate the server after publishing the card.
High	Stop asking users to paste secrets directly	Public MCP servers should prefer OAuth or browser-based auth guidance over in-band secret collection.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Adopt a current MCP protocol revision	Older protocol revisions reduce compatibility with newer clients and registry programs.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Close connector-publishing gaps	Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Document minimal scopes and return cleaner auth challenges	Modern clients expect granular scopes and step-up auth signals such as WWW-Authenticate scope hints.	Return granular scopes and WWW-Authenticate challenge hints instead of forcing overly broad auth upfront. Playbook Advertise the narrowest viable scopes in OAuth metadata. Return `WWW-Authenticate` challenges with scope or insufficient-scope hints when additional consent is needed. Revalidate with both public discovery and auth-required flows.
Medium	Publish OpenID configuration	OIDC metadata improves token validation and client compatibility.	Expose /.well-known/openid-configuration with issuer, jwks_uri, and supported grants. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Reduce tool-surface churn	Frequent add/remove or output-shape drift makes published connectors and cached tool snapshots brittle.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Support resumable HTTP sessions cleanly	Modern MCP clients increasingly expect resumable session behavior on streamable HTTP transports.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Low	Expose modern utility surfaces like completions, pagination, or tasks	Utility coverage improves interoperability with larger clients and long-lived agent workflows.	Expose completions, pagination, and task metadata where supported so larger clients can plan and resume work safely. Playbook Advertise `completions`, pagination cursors, and `tasks` only when they are actually supported. Return `nextCursor` on large list operations when pagination is available. Document task support and whether it requires step-up auth.
Low	Publish newer MCP capability signals	Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.

Point loss breakdown

Component	Current	Points missing
Transport Compliance	0/4	-4.0
Recovery Semantics	0/4	-4.0
Error Contract	0/4	-4.0
Trust Confidence	1.8/4	-2.2
Utility Coverage	2/4	-2.0
Safety Transparency	2/4	-2.0
Result Shape Stability	2/4	-2.0
Registry Consistency	2/4	-2.0
Rate Limit Semantics	2/4	-2.0
Prompt Contract	2/4	-2.0
Least Privilege Scope	2/4	-2.0
Egress SSRF Resilience	2/4	-2.0

Validation diff

Need at least two validation runs before diffing changes.

Tool snapshot diff & changelog

Need at least two validation runs before building a tool changelog.

Connector replay

Status

Missing

Backward compatible

Would break after refresh

Added tools

none

Removed tools

none

Additive output changes

none

Required-argument replay breaks

Tool	Added required args	Removed required args
No required-argument replay breaks detected.

Output-schema replay breaks

Tool	Removed properties	Added properties
No output-schema replay breaks detected.

Transport compliance drilldown

Probe status

Error

Transport

streamable-http

Session header

Protocol header

Bad protocol response

200

DELETE teardown

n/a

Expired session retry

n/a

Last-Event-ID visible

Issues: missing_session_id, missing_protocol_header, bad_protocol_not_rejected

Request association

Status

Missing

Advertised capabilities

none

Observed idle methods

none

Violating methods

none

Probe HTTP status

n/a

Issues

none

Utility coverage

Probe status

Missing

Completions

not detected

Completion probe target: { "type": "resource", "uri": "tandem-docs://stable/reference/agent-team-api/" }

Pagination

not detected

No nextCursor evidence.

Tasks

Missing

Advertised: no

Benchmark tasks

Benchmark task	Status	Evidence
Discover tools	Passes	`initialize` • OK `tools_list` • OK
Read-only fetch flow	Passes	`resource_read` • OK `read_only_tool_surface` • OK
OAuth-required connect	Degraded	`oauth_protected_resource` • Error `step_up_auth_probe` • Missing
Safe write flow with confirmation	Likely to fail	`action_safety_probe` • Error

Registry & provenance divergence

Probe status

Direct official match

yes

Drift fields

none

Field	Registry	Live server card
Title	n/a	n/a
Version	n/a	n/a
Homepage	n/a	n/a

Active alerts

No active alerts for the current server state.

Aliases & registry graph

Identifier	Source	Canonical	Score
`ac.tandem/docs-mcp`	official_registry	yes	70.41

Alias consolidation

Canonical identifier

ac.tandem/docs-mcp

Duplicate aliases

Registry sources

official_registry

Remote URLs

https://tandem.ac/mcp

Homepages

https://tandem.ac/docs-mcp

Source disagreements

Field	What differs	Observed values
No source disagreements detected.

Install snippets

Openai Connectors

Connector URL: https://tandem.ac/mcp
# No OAuth metadata detected.
# Server: ac.tandem/docs-mcp

Claude Desktop

{
  "mcpServers": {
    "docs-mcp": {
      "command": "npx",
      "args": ["mcp-remote", "https://tandem.ac/mcp"]
    }
  }
}

Smithery

smithery mcp add "https://tandem.ac/mcp"

Generic Http

curl -sS https://tandem.ac/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Agent access & tool surface

Live server tools

search_docs get_doc get_start_path recommend_next_docs answer_how_to get_tandem_guide warmup_docs_cache get_docs_cache_status

Observed from the latest live validation against https://tandem.ac/mcp. This is the target server surface, not Verify's own inspection tools.

Live capability counts

13 tools • 3 prompts • 50 resources

Counts come from the latest tools/list, prompts/list, and resources/list checks.

Inspect with Verify

search fetch search_servers recommend_servers get_server_report compare_servers

Use Verify itself to search, recommend, compare, and fetch the full report for ac.tandem/docs-mcp.

Direct machine links

JSON report • Compare this server • Verify MCP API

Claims & monitoring

Server ownership

No verified maintainer claim recorded.

Watch subscriptions

Teams: none

Alert routing

Active watches

Generic webhooks

Slack routes

Teams routes

Email routes

Watch	Team	Channels	Minimum severity
No active watch destinations.

Maintainer analytics

Validation Run Count

Average Latency Ms

2808.29

Healthy Run Ratio Recent

1.0

Registry Presence Count

Active Alert Count

Watcher Count

Verified Claim

False

Taxonomy Tags

development, search, web, cloud

Score Trend

70.41

Remediation Count

High Risk Tool Count

Destructive Tool Count

Exec Tool Count

Maintainer response quality

Score

16.67

Verified claim

Support contact

Changelog present

Incident notes present

Tool changes documented

✓

Annotation history

Annotation count

Maintainer annotations

No maintainer annotations have been recorded yet.

Maintainer rebuttals & expected behavior

No maintainer rebuttals or expected-behavior overrides are recorded yet.

Latest validation evidence

Latest summary

Healthy

Validation profile

remote_mcp

Started

Jul 31, 2026 05:33:11 AM UTC

Latency

2808.3 ms

Failures

oauth_authorization_server no authorization server
oauth_protected_resource Client error '404 Not Found' for url 'https://tandem.ac/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
openid_configuration no authorization server
server_card Client error '404 Not Found' for url 'https://tandem.ac/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
transport_compliance_probe Issues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200).

Checks

Check	Status	Latency	Evidence
`action_safety_probe`	Error	n/a	1 high-risk, 1 exec-capable tool(s); no clear auth boundary; safeguards=0; confirmation=none.
`advanced_capabilities_probe`	Warning	n/a	Only 3 capability signal(s): prompts, resource links, resources.
`connector_publishability_probe`	Warning	n/a	Publishability blockers: transport compliance, action safety, server card.
`connector_replay_probe`	Missing	n/a	No connector replay evidence recorded.
`determinism_probe`	OK	102.0 ms	Check completed
`initialize`	OK	370.8 ms	Protocol 2025-06-18
`interactive_flow_probe`	Missing	n/a	Check completed
`oauth_authorization_server`	Missing	n/a	no authorization server
`oauth_protected_resource`	Error	179.5 ms	Client error '404 Not Found' for url 'https://tandem.ac/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
`official_registry_probe`	OK	n/a	Check completed
`openid_configuration`	Missing	n/a	no authorization server
`probe_noise_resilience`	OK	373.0 ms	Fetched https://tandem.ac/robots.txt
`prompt_get`	OK	112.5 ms	1 prompt message(s) returned
`prompts_list`	OK	100.5 ms	3 prompt(s) exposed
`protocol_version_probe`	Warning	n/a	Claims 2025-06-18; 1 release(s) behind 2025-11-25.
`provenance_divergence_probe`	OK	n/a	Check completed
`request_association_probe`	Missing	n/a	No request-association capabilities were advertised.
`resource_read`	OK	280.7 ms	1 resource content item(s) returned
`resources_list`	OK	107.8 ms	50 resource item(s) exposed
`server_card`	Error	499.6 ms	Client error '404 Not Found' for url 'https://tandem.ac/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
`session_resume_probe`	Warning	n/a	no session id
`step_up_auth_probe`	Missing	n/a	No OAuth or incremental-scope signals detected.
`tool_snapshot_probe`	Missing	n/a	no historical snapshot
`tools_list`	OK	363.4 ms	13 tool(s) exposed
`transport_compliance_probe`	Error	101.8 ms	Issues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200).
`utility_coverage_probe`	Missing	104.5 ms	No completions evidence; no pagination evidence; tasks missing.

Raw evidence view

Show raw JSON evidence

{
  "checks": {
    "action_safety_probe": {
      "details": {
        "auth_present": false,
        "confirmation_signals": [],
        "safeguard_count": 0,
        "summary": {
          "bulk_access_tools": 3,
          "capability_distribution": {
            "admin": 4,
            "exec": 1,
            "export": 3,
            "filesystem": 6,
            "network": 2,
            "other": 2,
            "read": 8
          },
          "destructive_tools": 0,
          "egress_tools": 1,
          "exec_tools": 1,
          "high_risk_tools": 1,
          "risk_distribution": {
            "critical": 0,
            "high": 1,
            "low": 7,
            "medium": 5
          },
          "secret_tools": 0,
          "tool_count": 13
        }
      },
      "latency_ms": null,
      "status": "error"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": true,
          "resource_links": true,
          "resources": true,
          "roots": false,
          "sampling": false,
          "structured_outputs": false
        },
        "enabled": [
          "prompts",
          "resource_links",
          "resources"
        ],
        "enabled_count": 3,
        "initialize_capability_keys": [
          "prompts",
          "resources",
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "transport_compliance",
          "action_safety",
          "server_card"
        ],
        "criteria": {
          "action_safety": false,
          "auth_flow": true,
          "connector_replay": true,
          "initialize": true,
          "protocol_version": true,
          "remote_transport": true,
          "request_association": true,
          "server_card": false,
          "session_resume": true,
          "step_up_auth": true,
          "tool_surface": true,
          "tools_list": true,
          "transport_compliance": false
        },
        "high_risk_tools": 1,
        "tool_count": 13,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_replay_probe": {
      "details": {
        "reason": "no_historical_snapshot"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "determinism_probe": {
      "details": {
        "attempts": 2,
        "baseline_signature": "73dd9c8626a0051e0ab5c91ee42ba2a2c2e8668b24da92fb9f76ed0744013bb3",
        "errors": [],
        "matches": 2,
        "stable_ratio": 1.0,
        "successful": 2
      },
      "latency_ms": 102.0,
      "status": "ok"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 1,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "prompts": {},
              "resources": {},
              "tools": {}
            },
            "instructions": "Use tools/list and tools/call to retrieve Tandem documentation guidance.",
            "protocolVersion": "2025-06-18",
            "serverInfo": {
              "name": "ac.tandem/docs-mcp",
              "title": "Tandem Docs MCP",
              "version": "0.3.2"
            }
          }
        },
        "url": "https://tandem.ac/mcp"
      },
      "latency_ms": 370.78,
      "status": "ok"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": false,
        "prompt_available": true,
        "risk_hits": [],
        "safe_hits": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_authorization_server": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_protected_resource": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://tandem.ac/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://tandem.ac/.well-known/oauth-protected-resource"
      },
      "latency_ms": 179.53,
      "status": "error"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": true,
        "official_peer_count": 1,
        "registry_identifier": "ac.tandem/docs-mcp",
        "registry_source": "official_registry"
      },
      "latency_ms": null,
      "status": "ok"
    },
    "openid_configuration": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "probe_noise_resilience": {
      "details": {
        "headers": {
          "content-type": "text/plain; charset=utf-8"
        },
        "http_status": 200,
        "url": "https://tandem.ac/robots.txt"
      },
      "latency_ms": 373.02,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 4,
          "jsonrpc": "2.0",
          "result": {
            "description": "Guide an agent through installing Tandem Engine using the official Tandem docs and return the most relevant pages first.",
            "messages": [
              {
                "content": {
                  "text": "Guide an agent through installing Tandem Engine using the official Tandem docs and return the most relevant pages first.",
                  "type": "text"
                },
                "role": "user"
              }
            ]
          }
        },
        "prompt_name": "install_tandem_engine",
        "url": "https://tandem.ac/mcp"
      },
      "latency_ms": 112.46,
      "status": "ok"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 3,
          "jsonrpc": "2.0",
          "result": {
            "prompts": [
              {
                "description": "Prompt template for teaching an agent how to install Tandem Engine safely from the docs.",
                "name": "install_tandem_engine",
                "title": "Install Tandem Engine"
              },
              {
                "description": "Prompt template for helping an agent learn the Tandem Python SDK and prerequisites.",
                "name": "use_python_sdk",
                "title": "Use the Python SDK"
              },
              {
                "description": "Prompt template for helping an agent learn workflow building and orchestration patterns in Tandem.",
                "name": "build_workflows",
                "title": "Build Tandem workflows"
              }
            ]
          }
        },
        "url": "https://tandem.ac/mcp"
      },
      "latency_ms": 100.51,
      "status": "ok"
    },
    "protocol_version_probe": {
      "details": {
        "claimed_version": "2025-06-18",
        "lag_days": 160,
        "latest_known_version": "2025-11-25",
        "releases_behind": 1,
        "validator_protocol_version": "2025-03-26"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "provenance_divergence_probe": {
      "details": {
        "direct_official_match": true,
        "drift_fields": [],
        "metadata_document_count": 2,
        "registry_homepage": null,
        "registry_repository": null,
        "registry_title": null,
        "registry_version": null,
        "server_card_homepage": null,
        "server_card_repository": null,
        "server_card_title": null,
        "server_card_version": null
      },
      "latency_ms": null,
      "status": "ok"
    },
    "request_association_probe": {
      "details": {
        "reason": "no_request_association_capabilities_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "resource_read": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 6,
          "jsonrpc": "2.0",
          "result": {
            "contents": [
              {
                "mimeType": "text/plain",
                "text": "Agent Team API Endpoints Section titled \u201cEndpoints\u201d GET /agent-team/templates Section titled \u201cGET /agent-team/templates\u201d Returns loaded agent templates. GET /agent-team/instances Section titled \u201cGET /agent-team/instances\u201d Query params: missionID (optional) parentInstanceID (optional) status (optional: queued|running|completed|failed|cancelled ) GET /agent-team/missions Section titled \u201cGET /agent-team/missions\u201d Returns mission-level rollups across instances: instanceCount runningCount completedCount failedCount cancelledCount queuedCount tokenUsedTotal toolCallsUsedTotal stepsUsedTotal costUsedUsdTotal GET /agent-team/approvals Section titled \u201cGET /agent-team/approvals\u201d Returns: spawnApprovals : queued spawn approvals (request-only edges / approval-required paths) toolApprovals : pending permission requests scoped to agent-team sessions POST /agent-team/spawn Section titled \u201cPOST /agent-team/spawn\u201d Request body: { \"missionID\" : \" m1 \" , \"parentInstanceID\" : \" ins_parent \" , \"templateID\" : \" worker-default \" , \"role\" : \" worker \" , \"source\" : \" ui_action \" , \"justification\" : \" Implement focused task \" , \"budget_override\" : { \"max_tokens\" : 8000 , \"max_steps\" : 4 , \"max_tool_calls\" : 10 , \"max_duration_ms\" : 240000 , \"max_cost_usd\" : 1.25 } } Success response: { \"ok\" : true , \"missionID\" : \" m1 \" , \"instanceID\" : \" ins_... \" , \"sessionID\" : \" ses_... \" , \"runID\" : null , \"status\" : \" running \" , \"skillHash\" : \" sha256:... \" } Error response: { \"ok\" : false , \"code\" : \" spawn_policy_missing \" , \"error\" : \" spawn policy file missing \" , \"requiresUserApproval\" : false } If policy requires user approval, response shape is still 200 with: { \"ok\" : false , \"code\" : \" spawn_requires_approval \" , \"requiresUserApproval\" : true } Tool-driven spawn ( spawn_agent ) Section titled \u201cTool-driven spawn (spawn_agent)\u201d spawn_agent uses the same server-side policy/runtime gate as POST /agent-team/spawn . Invoke it through a session prompt: /tool spawn_agent {\"missionID\":\"m1\",\"role\":\"worker\",\"templateID\":\"worker-default\",\"source\":\"tool_call\",\"justification\":\"parallelize implementation\"} Tool response metadata shape: { \"ok\" : true , \"missionID\" : \" m1 \" , \"instanceID\" : \" ins_... \" , \"sessionID\" : \" ses_... \" , \"runID\" : null , \"status\" : \" running \" , \"skillHash\" : \" sha256:... \" } POST /agent-team/instance/{id}/cancel Section titled \u201cPOST /agent-team/instance/{id}/cancel\u201d Request body: { \"reason\" : \" manual stop \" } POST /agent-team/approvals/spawn/{id}/approve Section titled \u201cPOST /agent-team/approvals/spawn/{id}/approve\u201d Request body: { \"reason\" : \" approved from command center \" } Response: { \"ok\" : true , \"approvalID\" : \" appr_... \" , \"decision\" : \" approved \" , \"instanceID\" : \" ins_... \" , \"missionID\" : \" m1 \" , \"status\" : \" running \" } POST /agent-team/approvals/spawn/{id}/deny Section titled \u201cPOST /agent-team/approvals/spawn/{id}/deny\u201d Request body: { \"reason\" : \" not aligned with mission scope \" } Response: { \"ok\" : true , \"approvalID\" : \" appr_... \" , \"decision\" : \" denied \" , \"reason\" : \" not aligned with mission scope \" } Response: { \"ok\" : true , \"instanceID\" : \" ins_... \" , \"sessionID\" : \" ses_... \" , \"status\" : \" cancelled \" } POST /agent-team/mission/{id}/cancel Section titled \u201cPOST /agent-team/mission/{id}/cancel\u201d Request body: { \"reason\" : \" stop all mission agents \" } Response: { \"ok\" : true , \"missionID\" : \" m1 \" , \"cancelledInstances\" : 3 } POST /mission/{id}/event (orchestrator bridge fields) Section titled \u201cPOST /mission/{id}/event (orchestrator bridge fields)\u201d When mission runtime bridge is active, mission event responses include additive fields: orchestratorSpawns : spawn results triggered by mission_started orchestratorCancellations : cancellation summary triggered by mission_canceled Edit page Previous Spawn Policy Reference Next Agent Team Events",
                "uri": "tandem-docs://stable/reference/agent-team-api/"
              }
            ]
          }
        },
        "resource_uri": "tandem-docs://stable/reference/agent-team-api/",
        "url": "https://tandem.ac/mcp"
      },
      "latency_ms": 280.68,
      "status": "ok"
    },
    "resources_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 5,
          "jsonrpc": "2.0",
          "result": {
            "resources": [
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Agent-team HTTP API.",
                "mimeType": "text/plain",
                "name": "Agent Team Api",
                "title": "Agent Team Api",
                "uri": "tandem-docs://stable/reference/agent-team-api/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Agent-team event stream contract.",
                "mimeType": "text/plain",
                "name": "Agent Team Events",
                "title": "Agent Team Events",
                "uri": "tandem-docs://stable/reference/agent-team-events/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "System architecture overview.",
                "mimeType": "text/plain",
                "name": "Architecture",
                "title": "Architecture",
                "uri": "tandem-docs://stable/architecture/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Engine CLI commands.",
                "mimeType": "text/plain",
                "name": "Engine Commands",
                "title": "Engine Commands",
                "uri": "tandem-docs://stable/reference/engine-commands/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Engine testing guidance.",
                "mimeType": "text/plain",
                "name": "Engine Testing",
                "title": "Engine Testing",
                "uri": "tandem-docs://stable/engine-testing/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Eval Runner CLI reference for AI quality datasets and regression checks.",
                "mimeType": "text/plain",
                "name": "Eval Runner",
                "title": "Eval Runner",
                "uri": "tandem-docs://stable/eval-runner/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Canonical runtime reference for sessions, runs, context, memory, and channels.",
                "mimeType": "text/plain",
                "name": "How Tandem Works",
                "title": "How Tandem Works",
                "uri": "tandem-docs://stable/how-tandem-works/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Protocol and compatibility matrix.",
                "mimeType": "text/plain",
                "name": "Protocol Matrix",
                "title": "Protocol Matrix",
                "uri": "tandem-docs://stable/protocol-matrix/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Spawn policy and safety rules.",
                "mimeType": "text/plain",
                "name": "Spawn Policy",
                "title": "Spawn Policy",
                "uri": "tandem-docs://stable/reference/spawn-policy/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Tool API reference.",
                "mimeType": "text/plain",
                "name": "Tools",
                "title": "Tools",
                "uri": "tandem-docs://stable/reference/tools/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "TUI commands.",
                "mimeType": "text/plain",
                "name": "Tui Commands",
                "title": "Tui Commands",
                "uri": "tandem-docs://stable/reference/tui-commands/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Agent team architecture and behavior.",
                "mimeType": "text/plain",
                "name": "Agent Teams",
                "title": "Agent Teams",
                "uri": "tandem-docs://stable/agent-teams/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Sessions, context, and execution model.",
                "mimeType": "text/plain",
                "name": "Agents And Sessions",
                "title": "Agents And Sessions",
                "uri": "tandem-docs://stable/agents-and-sessions/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Slack, Discord, Telegram, and related integrations.",
                "mimeType": "text/plain",
                "name": "Channel Integrations",
                "title": "Channel Integrations",
                "uri": "tandem-docs://stable/channel-integrations/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Providers, keys, and system instructions.",
                "mimeType": "text/plain",
                "name": "Configuration",
                "title": "Configuration",
                "uri": "tandem-docs://stable/configuration/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Browser control panel and scaffolded app guidance.",
                "mimeType": "text/plain",
                "name": "Control Panel",
                "title": "Control Panel",
                "uri": "tandem-docs://stable/control-panel/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "First 10 minutes with Tandem Desktop.",
                "mimeType": "text/plain",
                "name": "First 10 Minutes",
                "title": "First 10 Minutes",
                "uri": "tandem-docs://stable/desktop/first-10-minutes/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Headless deployment from desktop workflows.",
                "mimeType": "text/plain",
                "name": "Headless Deployment",
                "title": "Headless Deployment",
                "uri": "tandem-docs://stable/desktop/headless-deployment/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Headless engine service mode.",
                "mimeType": "text/plain",
                "name": "Headless Service",
                "title": "Headless Service",
                "uri": "tandem-docs://stable/headless-service/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Interactive Learn walkthroughs.",
                "mimeType": "text/plain",
                "name": "Learn Walkthroughs",
                "title": "Learn Walkthroughs",
                "uri": "tandem-docs://stable/desktop/learn-walkthroughs/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Desktop overview.",
                "mimeType": "text/plain",
                "name": "Overview",
                "title": "Overview",
                "uri": "tandem-docs://stable/desktop/overview/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Settings and safety.",
                "mimeType": "text/plain",
                "name": "Settings And Safety",
                "title": "Settings And Safety",
                "uri": "tandem-docs://stable/desktop/settings-and-safety/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Desktop troubleshooting.",
                "mimeType": "text/plain",
                "name": "Troubleshooting",
                "title": "Troubleshooting",
                "uri": "tandem-docs://stable/desktop/troubleshooting/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Terminal UI guide.",
                "mimeType": "text/plain",
                "name": "Tui Guide",
                "title": "Tui Guide",
                "uri": "tandem-docs://stable/tui-guide/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Desktop workflows.",
                "mimeType": "text/plain",
                "name": "Workflows",
                "title": "Workflows",
                "uri": "tandem-docs://stable/desktop/workflows/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Safe Incident Monitor operating sequence for MCP-connected agents, SDK clients, and HTTP callers.",
                "mimeType": "text/plain",
                "name": "Agent Runtime Guide",
                "title": "Agent Runtime Guide",
                "uri": "tandem-docs://stable/incident-monitor/agent-runtime-guide/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Short checklist for agents creating, running, and maintaining Tandem workflows or missions.",
                "mimeType": "text/plain",
                "name": "Agent Workflow Mission Quickstart",
                "title": "Agent Workflow Mission Quickstart",
                "uri": "tandem-docs://stable/agent-workflow-mission-quickstart/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "End-to-end workflow examples, including the Linear repair-loop guard template for ACA-triggering issue webhooks.",
                "mimeType": "text/plain",
                "name": "Automation Examples For Teams",
                "title": "Automation Examples For Teams",
                "uri": "tandem-docs://stable/automation-examples-for-teams/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Direct webhook trigger setup for Automation V2, including Notion verification tokens and Linear issue webhook setup.",
                "mimeType": "text/plain",
                "name": "Automation V2 Webhooks",
                "title": "Automation V2 Webhooks",
                "uri": "tandem-docs://stable/automation-v2-webhooks/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "GitHub Projects coding-agent workflows.",
                "mimeType": "text/plain",
                "name": "Autonomous Coding Agents Github Projects",
                "title": "Autonomous Coding Agents Github Projects",
                "uri": "tandem-docs://stable/autonomous-coding-agents-github-projects/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Browser setup, install, and validation.",
                "mimeType": "text/plain",
                "name": "Browser Setup And Testing",
                "title": "Browser Setup And Testing",
                "uri": "tandem-docs://stable/browser-setup-and-testing/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "How agents should choose providers, defaults, and per-stage model overrides.",
                "mimeType": "text/plain",
                "name": "Choosing Providers And Models For Agents",
                "title": "Choosing Providers And Models For Agents",
                "uri": "tandem-docs://stable/choosing-providers-and-models-for-agents/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Which Tandem path to use and how to create, apply, schedule, and run it.",
                "mimeType": "text/plain",
                "name": "Creating And Running Workflows And Missions",
                "title": "Creating And Running Workflows And Missions",
                "uri": "tandem-docs://stable/creating-and-running-workflows-and-missions/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Destination router model for GitHub, Linear, webhooks, telemetry, MCP tools, and memory.",
                "mimeType": "text/plain",
                "name": "Destination Router",
                "title": "Destination Router",
                "uri": "tandem-docs://stable/incident-monitor/destination-router/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Destination adapter coverage and readiness requirements for governed Incident Monitor publishing.",
                "mimeType": "text/plain",
                "name": "Destinations",
                "title": "Destinations",
                "uri": "tandem-docs://stable/incident-monitor/destinations/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "How to obtain an engine token and authenticate SDK or HTTP calls.",
                "mimeType": "text/plain",
                "name": "Engine Authentication For Agents",
                "title": "Engine Authentication For Agents",
                "uri": "tandem-docs://stable/engine-authentication-for-agents/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Agent-facing onboarding order for client pilots, go-live smoke tests, and enterprise hardening.",
                "mimeType": "text/plain",
                "name": "Enterprise Client Onboarding Runbook",
                "title": "Enterprise Client Onboarding Runbook",
                "uri": "tandem-docs://stable/enterprise-client-onboarding-runbook/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Agent-facing enterprise setup guide for tenant-scoped memory, governed MCP setup, source bindings, connector credentials, and quarantine review.",
                "mimeType": "text/plain",
                "name": "Enterprise Data Governance",
                "title": "Enterprise Data Governance",
                "uri": "tandem-docs://stable/enterprise-data-governance/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "External source identity, monitored source bindings, and destination routing context.",
                "mimeType": "text/plain",
                "name": "External Sources",
                "title": "External Sources",
                "uri": "tandem-docs://stable/incident-monitor/external-sources/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Incident Monitor API and behavior reference for governed failure intake, drafts, approvals, routing, receipts, and destination publishes.",
                "mimeType": "text/plain",
                "name": "Incident Monitor",
                "title": "Incident Monitor",
                "uri": "tandem-docs://stable/reference/incident-monitor/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Configure external project log intake, scoped report keys, reset/replay debug actions, and monitored project setup.",
                "mimeType": "text/plain",
                "name": "Incident Monitor External Log Intake",
                "title": "Incident Monitor External Log Intake",
                "uri": "tandem-docs://stable/incident-monitor-external-log-intake/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Author, publish, operate, replay, and recover version-pinned goals spanning multiple Automation V2 workflow runs.",
                "mimeType": "text/plain",
                "name": "Long Running Multi Workflow Goals",
                "title": "Long Running Multi Workflow Goals",
                "uri": "tandem-docs://stable/long-running-multi-workflow-goals/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Automated agent workflows and MCP patterns.",
                "mimeType": "text/plain",
                "name": "Mcp Automated Agents",
                "title": "Mcp Automated Agents",
                "uri": "tandem-docs://stable/mcp-automated-agents/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Incident Monitor overview for governed intake, triage, routing, evidence, destination readiness, and receipts.",
                "mimeType": "text/plain",
                "name": "Overview",
                "title": "Overview",
                "uri": "tandem-docs://stable/incident-monitor/overview/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Production governance guidance for deployment cards, posture checks, assessment reports, protected evidence, and receipts.",
                "mimeType": "text/plain",
                "name": "Production Governance",
                "title": "Production Governance",
                "uri": "tandem-docs://stable/incident-monitor/production-governance/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "How to prompt Tandem workflows, missions, and staged recurring operations.",
                "mimeType": "text/plain",
                "name": "Prompting Workflows And Missions",
                "title": "Prompting Workflows And Missions",
                "uri": "tandem-docs://stable/prompting-workflows-and-missions/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Python SDK.",
                "mimeType": "text/plain",
                "name": "Python",
                "title": "Python",
                "uri": "tandem-docs://stable/sdk/python/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "SDK automation scheduling.",
                "mimeType": "text/plain",
                "name": "Scheduling Automations",
                "title": "Scheduling Automations",
                "uri": "tandem-docs://stable/sdk/scheduling-automations/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "SDK landing page.",
                "mimeType": "text/plain",
                "name": "Sdk",
                "title": "Sdk",
                "uri": "tandem-docs://stable/sdk/"
              },
              {
                "annotations": {
                  "audience": [
                    "assistant"
                  ],
                  "priority": 100
                },
                "description": "Read-only authority inventory, posture assessment, scenario packs, and remediation routing.",
                "mimeType": "text/plain",
                "name": "Security Posture",
                "title": "Security Posture",
                "uri": "tandem-docs://stable/incident-monitor/security-posture/"
              }
            ]
          }
        },
        "url": "https://tandem.ac/mcp"
      },
      "latency_ms": 107.81,
      "status": "ok"
    },
    "server_card": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://tandem.ac/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://tandem.ac/.well-known/mcp/server-card.json"
      },
      "latency_ms": 499.64,
      "status": "error"
    },
    "session_resume_probe": {
      "details": {
        "protocol_version": "2025-06-18",
        "reason": "no_session_id",
        "resume_expected": true,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "step_up_auth_probe": {
      "details": {
        "auth_required_checks": [],
        "broad_scopes": [],
        "challenge_headers": [],
        "minimal_scope_documented": false,
        "oauth_present": false,
        "scope_specificity_ratio": 0.0,
        "step_up_signals": [],
        "supported_scopes": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tool_snapshot_probe": {
      "details": {
        "current_tool_count": 13,
        "reason": "no_historical_snapshot"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Search Tandem docs"
                },
                "description": "Search the published Tandem docs index for relevant pages.",
                "inputSchema": {
                  "properties": {
                    "audience": {
                      "description": "Optional audience filter such as developer, desktop user, or operator.",
                      "type": "string"
                    },
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable. Use next, refs/<sha>, or releases/<version> only when explicitly needed.",
                      "type": "string"
                    },
                    "engine_version": {
                      "description": "Optional Tandem engine version hint. If supplied without docs_ref, the MCP still defaults to stable unless a matching versioned docs ref is configured.",
                      "type": "string"
                    },
                    "limit": {
                      "description": "Maximum number of matching docs pages to return.",
                      "maximum": 20,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "The Tandem question, task, or keyword query to search for.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "query"
                  ],
                  "type": "object"
                },
                "name": "search_docs"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Fetch a docs page"
                },
                "description": "Fetch and normalize a published Tandem docs page by path or URL.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "engine_version": {
                      "description": "Optional Tandem engine version hint for compatibility checks.",
                      "type": "string"
                    },
                    "path": {
                      "description": "Docs path like /sdk/python/ or a full Tandem docs URL.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "path"
                  ],
                  "type": "object"
                },
                "name": "get_doc"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get a starting docs path"
                },
                "description": "Recommend the best Tandem docs starting path for a desktop user, server admin, or developer.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "role": {
                      "description": "The user role to optimize the docs starting point for.",
                      "enum": [
                        "desktop",
                        "server_admin",
                        "developer"
                      ],
                      "type": "string"
                    }
                  },
                  "required": [
                    "role"
                  ],
                  "type": "object"
                },
                "name": "get_start_path"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Recommend next docs"
                },
                "description": "Recommend the next Tandem docs to read after a current page, optionally biased toward a goal.",
                "inputSchema": {
                  "properties": {
                    "current_path": {
                      "description": "Current Tandem docs path the user has already read.",
                      "type": "string"
                    },
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "goal": {
                      "description": "Optional goal such as install Tandem, use the Python SDK, or build workflows.",
                      "type": "string"
                    },
                    "limit": {
                      "description": "Maximum number of next-doc recommendations to return.",
                      "maximum": 10,
                      "minimum": 1,
                      "type": "integer"
                    }
                  },
                  "required": [
                    "current_path"
                  ],
                  "type": "object"
                },
                "name": "recommend_next_docs"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Answer a Tandem how-to question"
                },
                "description": "Answer how to install or use Tandem, build workflows, or use the SDKs by synthesizing relevant published docs.",
                "inputSchema": {
                  "properties": {
                    "audience": {
                      "description": "Optional audience hint such as developer, desktop user, or operator.",
                      "type": "string"
                    },
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "engine_version": {
                      "description": "Optional Tandem engine version hint. Prefer stable docs for installed engines.",
                      "type": "string"
                    },
                    "limit": {
                      "description": "Maximum number of supporting docs recommendations to include.",
                      "maximum": 10,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "task": {
                      "description": "The Tandem task or question that needs a docs-grounded answer.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "task"
                  ],
                  "type": "object"
                },
                "name": "answer_how_to"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get a Tandem guide"
                },
                "description": "Return a structured Tandem learning guide for install-engine, python-sdk, typescript-sdk, build-workflows, or headless-deploy.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "topic": {
                      "description": "Named Tandem learning guide to return.",
                      "enum": [
                        "install-engine",
                        "python-sdk",
                        "typescript-sdk",
                        "build-workflows",
                        "headless-deploy"
                      ],
                      "type": "string"
                    }
                  },
                  "required": [
                    "topic"
                  ],
                  "type": "object"
                },
                "name": "get_tandem_guide"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Warm docs cache"
                },
                "description": "Refresh the docs index and preload the most important Tandem docs pages into cache.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "force_refresh": {
                      "description": "Whether to bypass cache and force fresh upstream fetches first.",
                      "type": "boolean"
                    }
                  },
                  "type": "object"
                },
                "name": "warmup_docs_cache"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Inspect docs cache status"
                },
                "description": "Inspect the current docs cache state for index sources and warmed pages.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "get_docs_cache_status"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Refresh docs index"
                },
                "description": "Force-refresh docs indexes and report whether data came from the network, cache, or stale fallback.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "force_refresh": {
                      "description": "Whether to bypass cache and force a network refresh attempt.",
                      "type": "boolean"
                    }
                  },
                  "type": "object"
                },
                "name": "refresh_docs_index"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Refresh one docs page"
                },
                "description": "Force-refresh a docs page and report whether content came from the network, cache, or stale fallback.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "force_refresh": {
                      "description": "Whether to bypass cache and force a network refresh attempt.",
                      "type": "boolean"
                    },
                    "path": {
                      "description": "Docs path like /start-here/ or /sdk/python/ to refresh.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "path"
                  ],
                  "type": "object"
                },
                "name": "refresh_doc_page"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "title": "Invalidate docs cache"
                },
                "description": "Invalidate docs cache entries for index data, all pages, or a specific page path.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Optional docs ref to scope page/index cache invalidation.",
                      "type": "string"
                    },
                    "path": {
                      "description": "Required when target is page; identifies the specific docs path to invalidate.",
                      "type": "string"
                    },
                    "target": {
                      "description": "Which cache area to invalidate.",
                      "enum": [
                        "all",
                        "index",
                        "pages",
                        "page"
                      ],
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "invalidate_docs_cache"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Compare docs index refresh"
                },
                "description": "Force-refresh the docs indexes and return before/after hashes so content changes can be proven.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "compare_docs_index_refresh"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Compare page refresh"
                },
                "description": "Force-refresh a docs page and return before/after hashes so page content changes can be proven.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "path": {
                      "description": "Docs path like /start-here/ or /sdk/python/ to compare before and after refresh.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "path"
                  ],
                  "type": "object"
                },
                "name": "compare_doc_page_refresh"
              }
            ]
          }
        },
        "url": "https://tandem.ac/mcp"
      },
      "latency_ms": 363.45,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "application/json"
        },
        "bad_protocol_payload": {
          "id": 410,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Search Tandem docs"
                },
                "description": "Search the published Tandem docs index for relevant pages.",
                "inputSchema": {
                  "properties": {
                    "audience": {
                      "description": "Optional audience filter such as developer, desktop user, or operator.",
                      "type": "string"
                    },
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable. Use next, refs/<sha>, or releases/<version> only when explicitly needed.",
                      "type": "string"
                    },
                    "engine_version": {
                      "description": "Optional Tandem engine version hint. If supplied without docs_ref, the MCP still defaults to stable unless a matching versioned docs ref is configured.",
                      "type": "string"
                    },
                    "limit": {
                      "description": "Maximum number of matching docs pages to return.",
                      "maximum": 20,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "The Tandem question, task, or keyword query to search for.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "query"
                  ],
                  "type": "object"
                },
                "name": "search_docs"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Fetch a docs page"
                },
                "description": "Fetch and normalize a published Tandem docs page by path or URL.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "engine_version": {
                      "description": "Optional Tandem engine version hint for compatibility checks.",
                      "type": "string"
                    },
                    "path": {
                      "description": "Docs path like /sdk/python/ or a full Tandem docs URL.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "path"
                  ],
                  "type": "object"
                },
                "name": "get_doc"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get a starting docs path"
                },
                "description": "Recommend the best Tandem docs starting path for a desktop user, server admin, or developer.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "role": {
                      "description": "The user role to optimize the docs starting point for.",
                      "enum": [
                        "desktop",
                        "server_admin",
                        "developer"
                      ],
                      "type": "string"
                    }
                  },
                  "required": [
                    "role"
                  ],
                  "type": "object"
                },
                "name": "get_start_path"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Recommend next docs"
                },
                "description": "Recommend the next Tandem docs to read after a current page, optionally biased toward a goal.",
                "inputSchema": {
                  "properties": {
                    "current_path": {
                      "description": "Current Tandem docs path the user has already read.",
                      "type": "string"
                    },
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "goal": {
                      "description": "Optional goal such as install Tandem, use the Python SDK, or build workflows.",
                      "type": "string"
                    },
                    "limit": {
                      "description": "Maximum number of next-doc recommendations to return.",
                      "maximum": 10,
                      "minimum": 1,
                      "type": "integer"
                    }
                  },
                  "required": [
                    "current_path"
                  ],
                  "type": "object"
                },
                "name": "recommend_next_docs"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Answer a Tandem how-to question"
                },
                "description": "Answer how to install or use Tandem, build workflows, or use the SDKs by synthesizing relevant published docs.",
                "inputSchema": {
                  "properties": {
                    "audience": {
                      "description": "Optional audience hint such as developer, desktop user, or operator.",
                      "type": "string"
                    },
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "engine_version": {
                      "description": "Optional Tandem engine version hint. Prefer stable docs for installed engines.",
                      "type": "string"
                    },
                    "limit": {
                      "description": "Maximum number of supporting docs recommendations to include.",
                      "maximum": 10,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "task": {
                      "description": "The Tandem task or question that needs a docs-grounded answer.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "task"
                  ],
                  "type": "object"
                },
                "name": "answer_how_to"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get a Tandem guide"
                },
                "description": "Return a structured Tandem learning guide for install-engine, python-sdk, typescript-sdk, build-workflows, or headless-deploy.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "topic": {
                      "description": "Named Tandem learning guide to return.",
                      "enum": [
                        "install-engine",
                        "python-sdk",
                        "typescript-sdk",
                        "build-workflows",
                        "headless-deploy"
                      ],
                      "type": "string"
                    }
                  },
                  "required": [
                    "topic"
                  ],
                  "type": "object"
                },
                "name": "get_tandem_guide"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Warm docs cache"
                },
                "description": "Refresh the docs index and preload the most important Tandem docs pages into cache.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "force_refresh": {
                      "description": "Whether to bypass cache and force fresh upstream fetches first.",
                      "type": "boolean"
                    }
                  },
                  "type": "object"
                },
                "name": "warmup_docs_cache"
              },
              {
                "annotations": {
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Inspect docs cache status"
                },
                "description": "Inspect the current docs cache state for index sources and warmed pages.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "get_docs_cache_status"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Refresh docs index"
                },
                "description": "Force-refresh docs indexes and report whether data came from the network, cache, or stale fallback.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "force_refresh": {
                      "description": "Whether to bypass cache and force a network refresh attempt.",
                      "type": "boolean"
                    }
                  },
                  "type": "object"
                },
                "name": "refresh_docs_index"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Refresh one docs page"
                },
                "description": "Force-refresh a docs page and report whether content came from the network, cache, or stale fallback.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "force_refresh": {
                      "description": "Whether to bypass cache and force a network refresh attempt.",
                      "type": "boolean"
                    },
                    "path": {
                      "description": "Docs path like /start-here/ or /sdk/python/ to refresh.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "path"
                  ],
                  "type": "object"
                },
                "name": "refresh_doc_page"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "title": "Invalidate docs cache"
                },
                "description": "Invalidate docs cache entries for index data, all pages, or a specific page path.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Optional docs ref to scope page/index cache invalidation.",
                      "type": "string"
                    },
                    "path": {
                      "description": "Required when target is page; identifies the specific docs path to invalidate.",
                      "type": "string"
                    },
                    "target": {
                      "description": "Which cache area to invalidate.",
                      "enum": [
                        "all",
                        "index",
                        "pages",
                        "page"
                      ],
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "invalidate_docs_cache"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Compare docs index refresh"
                },
                "description": "Force-refresh the docs indexes and return before/after hashes so content changes can be proven.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "compare_docs_index_refresh"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "title": "Compare page refresh"
                },
                "description": "Force-refresh a docs page and return before/after hashes so page content changes can be proven.",
                "inputSchema": {
                  "properties": {
                    "docs_ref": {
                      "description": "Docs channel or immutable ref. Defaults to stable.",
                      "type": "string"
                    },
                    "path": {
                      "description": "Docs path like /start-here/ or /sdk/python/ to compare before and after refresh.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "path"
                  ],
                  "type": "object"
                },
                "name": "compare_doc_page_refresh"
              }
            ]
          }
        },
        "bad_protocol_status_code": 200,
        "delete_error": null,
        "delete_status_code": null,
        "expired_session_error": null,
        "expired_session_status_code": null,
        "issues": [
          "missing_session_id",
          "missing_protocol_header",
          "bad_protocol_not_rejected"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": false,
        "requested_protocol_version": "2025-06-18",
        "session_id_present": false,
        "transport": "streamable-http"
      },
      "latency_ms": 101.8,
      "status": "error"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": {
            "type": "resource",
            "uri": "tandem-docs://stable/reference/agent-team-api/"
          }
        },
        "initialize_capability_keys": [
          "prompts",
          "resources",
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 404,
          "probe_status": "missing"
        }
      },
      "latency_ms": 104.48,
      "status": "missing"
    }
  },
  "failures": {
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "error": "Client error '404 Not Found' for url 'https://tandem.ac/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://tandem.ac/.well-known/oauth-protected-resource"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "server_card": {
      "error": "Client error '404 Not Found' for url 'https://tandem.ac/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://tandem.ac/.well-known/mcp/server-card.json"
    },
    "transport_compliance_probe": {
      "bad_protocol_error": null,
      "bad_protocol_headers": {
        "content-type": "application/json"
      },
      "bad_protocol_payload": {
        "id": 410,
        "jsonrpc": "2.0",
        "result": {
          "tools": [
            {
              "annotations": {
                "idempotentHint": true,
                "openWorldHint": true,
                "readOnlyHint": true,
                "title": "Search Tandem docs"
              },
              "description": "Search the published Tandem docs index for relevant pages.",
              "inputSchema": {
                "properties": {
                  "audience": {
                    "description": "Optional audience filter such as developer, desktop user, or operator.",
                    "type": "string"
                  },
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable. Use next, refs/<sha>, or releases/<version> only when explicitly needed.",
                    "type": "string"
                  },
                  "engine_version": {
                    "description": "Optional Tandem engine version hint. If supplied without docs_ref, the MCP still defaults to stable unless a matching versioned docs ref is configured.",
                    "type": "string"
                  },
                  "limit": {
                    "description": "Maximum number of matching docs pages to return.",
                    "maximum": 20,
                    "minimum": 1,
                    "type": "integer"
                  },
                  "query": {
                    "description": "The Tandem question, task, or keyword query to search for.",
                    "type": "string"
                  }
                },
                "required": [
                  "query"
                ],
                "type": "object"
              },
              "name": "search_docs"
            },
            {
              "annotations": {
                "idempotentHint": true,
                "openWorldHint": true,
                "readOnlyHint": true,
                "title": "Fetch a docs page"
              },
              "description": "Fetch and normalize a published Tandem docs page by path or URL.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "engine_version": {
                    "description": "Optional Tandem engine version hint for compatibility checks.",
                    "type": "string"
                  },
                  "path": {
                    "description": "Docs path like /sdk/python/ or a full Tandem docs URL.",
                    "type": "string"
                  }
                },
                "required": [
                  "path"
                ],
                "type": "object"
              },
              "name": "get_doc"
            },
            {
              "annotations": {
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true,
                "title": "Get a starting docs path"
              },
              "description": "Recommend the best Tandem docs starting path for a desktop user, server admin, or developer.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "role": {
                    "description": "The user role to optimize the docs starting point for.",
                    "enum": [
                      "desktop",
                      "server_admin",
                      "developer"
                    ],
                    "type": "string"
                  }
                },
                "required": [
                  "role"
                ],
                "type": "object"
              },
              "name": "get_start_path"
            },
            {
              "annotations": {
                "idempotentHint": true,
                "openWorldHint": true,
                "readOnlyHint": true,
                "title": "Recommend next docs"
              },
              "description": "Recommend the next Tandem docs to read after a current page, optionally biased toward a goal.",
              "inputSchema": {
                "properties": {
                  "current_path": {
                    "description": "Current Tandem docs path the user has already read.",
                    "type": "string"
                  },
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "goal": {
                    "description": "Optional goal such as install Tandem, use the Python SDK, or build workflows.",
                    "type": "string"
                  },
                  "limit": {
                    "description": "Maximum number of next-doc recommendations to return.",
                    "maximum": 10,
                    "minimum": 1,
                    "type": "integer"
                  }
                },
                "required": [
                  "current_path"
                ],
                "type": "object"
              },
              "name": "recommend_next_docs"
            },
            {
              "annotations": {
                "idempotentHint": true,
                "openWorldHint": true,
                "readOnlyHint": true,
                "title": "Answer a Tandem how-to question"
              },
              "description": "Answer how to install or use Tandem, build workflows, or use the SDKs by synthesizing relevant published docs.",
              "inputSchema": {
                "properties": {
                  "audience": {
                    "description": "Optional audience hint such as developer, desktop user, or operator.",
                    "type": "string"
                  },
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "engine_version": {
                    "description": "Optional Tandem engine version hint. Prefer stable docs for installed engines.",
                    "type": "string"
                  },
                  "limit": {
                    "description": "Maximum number of supporting docs recommendations to include.",
                    "maximum": 10,
                    "minimum": 1,
                    "type": "integer"
                  },
                  "task": {
                    "description": "The Tandem task or question that needs a docs-grounded answer.",
                    "type": "string"
                  }
                },
                "required": [
                  "task"
                ],
                "type": "object"
              },
              "name": "answer_how_to"
            },
            {
              "annotations": {
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true,
                "title": "Get a Tandem guide"
              },
              "description": "Return a structured Tandem learning guide for install-engine, python-sdk, typescript-sdk, build-workflows, or headless-deploy.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "topic": {
                    "description": "Named Tandem learning guide to return.",
                    "enum": [
                      "install-engine",
                      "python-sdk",
                      "typescript-sdk",
                      "build-workflows",
                      "headless-deploy"
                    ],
                    "type": "string"
                  }
                },
                "required": [
                  "topic"
                ],
                "type": "object"
              },
              "name": "get_tandem_guide"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "title": "Warm docs cache"
              },
              "description": "Refresh the docs index and preload the most important Tandem docs pages into cache.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "force_refresh": {
                    "description": "Whether to bypass cache and force fresh upstream fetches first.",
                    "type": "boolean"
                  }
                },
                "type": "object"
              },
              "name": "warmup_docs_cache"
            },
            {
              "annotations": {
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true,
                "title": "Inspect docs cache status"
              },
              "description": "Inspect the current docs cache state for index sources and warmed pages.",
              "inputSchema": {
                "properties": {},
                "type": "object"
              },
              "name": "get_docs_cache_status"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "title": "Refresh docs index"
              },
              "description": "Force-refresh docs indexes and report whether data came from the network, cache, or stale fallback.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "force_refresh": {
                    "description": "Whether to bypass cache and force a network refresh attempt.",
                    "type": "boolean"
                  }
                },
                "type": "object"
              },
              "name": "refresh_docs_index"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "title": "Refresh one docs page"
              },
              "description": "Force-refresh a docs page and report whether content came from the network, cache, or stale fallback.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "force_refresh": {
                    "description": "Whether to bypass cache and force a network refresh attempt.",
                    "type": "boolean"
                  },
                  "path": {
                    "description": "Docs path like /start-here/ or /sdk/python/ to refresh.",
                    "type": "string"
                  }
                },
                "required": [
                  "path"
                ],
                "type": "object"
              },
              "name": "refresh_doc_page"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "title": "Invalidate docs cache"
              },
              "description": "Invalidate docs cache entries for index data, all pages, or a specific page path.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Optional docs ref to scope page/index cache invalidation.",
                    "type": "string"
                  },
                  "path": {
                    "description": "Required when target is page; identifies the specific docs path to invalidate.",
                    "type": "string"
                  },
                  "target": {
                    "description": "Which cache area to invalidate.",
                    "enum": [
                      "all",
                      "index",
                      "pages",
                      "page"
                    ],
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "name": "invalidate_docs_cache"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "title": "Compare docs index refresh"
              },
              "description": "Force-refresh the docs indexes and return before/after hashes so content changes can be proven.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "name": "compare_docs_index_refresh"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "title": "Compare page refresh"
              },
              "description": "Force-refresh a docs page and return before/after hashes so page content changes can be proven.",
              "inputSchema": {
                "properties": {
                  "docs_ref": {
                    "description": "Docs channel or immutable ref. Defaults to stable.",
                    "type": "string"
                  },
                  "path": {
                    "description": "Docs path like /start-here/ or /sdk/python/ to compare before and after refresh.",
                    "type": "string"
                  }
                },
                "required": [
                  "path"
                ],
                "type": "object"
              },
              "name": "compare_doc_page_refresh"
            }
          ]
        }
      },
      "bad_protocol_status_code": 200,
      "delete_error": null,
      "delete_status_code": null,
      "expired_session_error": null,
      "expired_session_status_code": null,
      "issues": [
        "missing_session_id",
        "missing_protocol_header",
        "bad_protocol_not_rejected"
      ],
      "last_event_id_visible": false,
      "protocol_header_present": false,
      "requested_protocol_version": "2025-06-18",
      "session_id_present": false,
      "transport": "streamable-http"
    }
  },
  "remote_url": "https://tandem.ac/mcp",
  "server_card_payload": null,
  "server_identifier": "ac.tandem/docs-mcp"
}

Known versions

0.3.2

Validation history

7 day score delta

n/a

30 day score delta

n/a

Recent healthy ratio

100%

Freshness

1.4h

Timestamp	Status	Score	Latency	Tools
Jul 31, 2026 05:33:13 AM UTC	Healthy	70.4	2808.3 ms	13

Validation timeline

Validated	Summary	Score	Protocol	Auth mode	Tools	High-risk tools	Changes
Jul 31, 2026 05:33:13 AM UTC	Healthy	70.4	2025-06-18	public	13	1	none

Recent validation runs

Started	Status	Summary	Latency	Checks
Jul 31, 2026 05:33:11 AM UTC	Completed	Healthy	2808.3 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe