← Back to search

Search • Governance: TrustOps / Gateway / Compare • Publishers: Claim / Badges / Profiles • Research: Trust Index / Rankings • Docs: Methodology / Security / MCP API • Pricing • Claim/Manage

github-api-evangelist/agnost-ai

api-evangelist/agnost-ai

Agnost AI is a production monitoring and product-analytics platform for teams building chat and voice AI agents. It continuously reads production agent conversations, MCP tool calls, and OpenTelemetry traces, clusters recurring intents, feature requests, frustration, and failure patterns, and catches agent failures that offline evals miss.

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

DECISION SUMMARY

Block For Production

Score

11.2

Top 95.5% of 75,223 scored public servers

Confidence

Medium

Based on evidence completeness, recency, and validation density.

Evidence age

5.0h old

Freshness: fresh. Snapshot trustsnap_520d233faf165c3e.

Top risk drivers

Transport Fidelity
Tool Surface Design
Tool Snapshot Churn

Recommended actions

Make tools/list succeed unauthenticated when possible, or document the auth flow in the server card.
Allow initialize to succeed consistently, or return a deterministic auth-required response with clear metadata.
Fix the failing checks first, then revalidate to confirm the recovery path.

Production decision

Block for production

failing live status + score below evaluation threshold

Current score

11.2

Snapshot trustsnap_520d233faf165c3e

Next action

revalidate, add safeguards, export policy

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

Compare alternatives Export policy Open report JSON

Observed Attention

No observed attention

No observed attention in the current 30-day window.

No segmented attention signals observed in the current window.

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

Risk Compatibility Evidence Fix it Governance

Status

Failing

Score

11.2

Transport

unknown

Tools

Ownership

Unclaimed

Claim, revalidate, or manage this server

Current trust snapshot

Snapshot ID

trustsnap_520d233faf165c3e

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

Snapshot generated

Aug 05, 2026 12:57:55 AM UTC

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

Last validated

Aug 04, 2026 07:58:35 PM UTC

Age: 4.99h • evidence age tier: Verified in last 24h • display score: 11.21

Canonical machine links

Compare index

/compare.json

Compare API

/v1/compare?server=github-api-evangelist%2Fagnost-ai

Trust summary

/v1/servers/github-api-evangelist/agnost-ai/trust-summary

Report JSON

/v1/servers/github-api-evangelist/agnost-ai/report

Policy export

/v1/servers/github-api-evangelist/agnost-ai/policy

Badge metadata

/v1/servers/github-api-evangelist/agnost-ai/badge

Ledger evidence

/v1/servers/github-api-evangelist/agnost-ai/ledger

Human compare URL

/compare?server=github-api-evangelist%2Fagnost-ai

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.

Evidence age tier

Verified in last 24h

Policy SLA (contractual, distinct from the public 24h freshness window): 168.0h • confidence-weighted score (display score discounted for evidence age and confidence -- an internal TrustOps input, not the public score): 8.1 • evidence too old to display: ✕

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 Write-Safe 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

score_below_hosting_threshold server_not_healthy_or_degraded remote_endpoint_missing latest_validation_not_passing

Deployment	Status	Endpoint	Release
No hosted runtime deployments yet.

Critical alerts

Production verdicts degrade quickly when critical alerts are active.

Evidence confidence

Confidence score

72.5

Based on 6 recent validations, 26 captured checks, and validation age of 5.0 hours.

Live checks captured

More direct checks increase trust in the current verdict.

Validation age

5.0h

Lower age means fresher evidence.

Recommended for

No recommendation profile is available yet.

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

Not client-compatible

Requires a streamable HTTP endpoint.; Requires a public remote MCP endpoint.; OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Initialize must be reachable.; tools/list must succeed.; OAuth interoperability should be strong.

Confidence: medium (72.5)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • Missing
tools_list • Missing
transport_compliance_probe • Missing
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

Not client-compatible

Confidence: medium (72.5)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • Missing
tools_list • Missing
transport_compliance_probe • Missing

Write-action publishing

Publishing allowed

Current write surface is bounded enough for cautious review with production policy controls.

Confidence: medium (72.5)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history

Disagreements: none

action_safety_probe • OK

Snapshot churn risk

Low

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

Confidence: medium (72.5)

Evidence provenance

Winner: history

Supporting sources: history, live_validation

Disagreements: none

tool_snapshot_probe • Missing
connector_replay_probe • Missing

Client compatibility gate details

ChatGPT custom connector

Not client-compatible

Remediation checklist

Requires a streamable HTTP endpoint.
Requires a public remote MCP endpoint.
OpenAI connectors expect OAuth for remote server auth.
Dynamic client registration materially improves connector setup.
Initialize must be reachable.
tools/list must succeed.

Claude remote MCP

Not client-compatible

Remediation checklist

Requires a reachable remote MCP URL.
Initialize must succeed or cleanly request auth.
tools/list must succeed.
A useful Claude integration needs at least one exposed tool.
Claude remote wrappers expect HTTP/SSE transports.
The tool surface is not limited to search/fetch-style read tools.

Write-safe publishing

Ready

Remediation checklist

No explicit blockers recorded.

Verdict traces

Production verdict

Metadata only

No live validation evidence exists yet for this entry.

Confidence: medium (72.5)

Winning source: live_validation

Triggering alerts

server_failing • critical • Latest validation is failing

Client verdict trace table

Verdict	Status	Checks	Winning source	Conflicts
`openai_connectors`	Not client-compatible	initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe	live_validation	none
`claude_desktop`	Not client-compatible	initialize, tools_list, transport_compliance_probe	live_validation	none
`unsafe_for_write_actions`	Publishing allowed	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

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

Claude remote MCP compatibility

Compatible with review

Requires a reachable remote MCP URL.; Initialize must succeed or cleanly request auth.; tools/list must succeed.; A useful Claude integration needs at least one exposed tool.; Claude remote wrappers expect HTTP/SSE transports. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.

Search Fetch Only: No
Write Actions Present: No
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

remote_http_endpoint: Likely to fail
oauth_discovery: Degraded
frozen_tool_snapshot_refresh: Passes
request_association: Passes

Anthropic remote MCP fixture

Degraded

remote_transport: Likely to fail
tool_discovery: Likely to fail
auth_connect: Likely to fail
safe_write_review: Passes

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

0.0

Validation success 30d

0.0

Mean time to recover

n/a

Breaking diffs 30d

Registry drift frequency 30d

Snapshot changes 30d

Incident & change feed

Timestamp	Event	Details
Aug 04, 2026 07:58:35 PM UTC	Latest validation: failing	Score 18.7 with status failing.
Aug 04, 2026 07:58:35 PM UTC	Score changed	Score delta -3.6 versus the previous run.
Aug 04, 2026 10:57:47 AM UTC	Score changed	Score delta +0.2 versus the previous run.
Aug 04, 2026 05:23:41 AM UTC	Score changed	Score delta +0.1 versus the previous run.

Capabilities

OAuth: ✕
DCR/CIMD: ✕
Prompts: ✕
Homepage: https://github.com/api-evangelist/agnost-ai
Docs: https://github.com/api-evangelist/agnost-ai
Support: https://github.com/api-evangelist/agnost-ai
Icon: https://avatars.githubusercontent.com/u/3026872?v=4
Remote endpoint: none
Server card: none

Use-case taxonomy

development communication automation monitoring

Security posture

Tools analyzed

High-risk tools

Destructive tools

Exec tools

Egress tools

Secret tools

Bulk-access tools

Risk distribution

none

Agent Commerce & Payment Readiness - Beta

Commerce signal is weak and payment capability is none -- below the bar for a full commerce assessment on this page.

Tool capability & risk inventory

No tool inventory available from the latest validation run.

Write-action governance

Governance status

Safe to publish

✓

Auth boundary

public_or_unclear

Blast radius

Low

High-risk tools

Confirmation signals

none

Safeguard count

Status detail: No unsafe write-action governance gaps detected on the latest validation.

Tool	Risk	Flags	Safeguards
No high-risk tools were detected on the latest run.

Action-controls diff

Need at least two validation runs before diffing action controls.

Why this score?

Access & Protocol

12.5/44

Connectivity, auth, and transport expectations for common clients.

Interface Quality

10/56

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

Security Posture

14.5/36

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

Reliability & Trust

15.27/24

Operational stability, consistency, and trustworthiness over time.

Discovery & Governance

19.95/28

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

Adoption & Market

3.6/8

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

Algorithmic score breakdown

Auth Operability

0/4

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

0/4

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

Backward Compatibility

4/4

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

1.5/4

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

Task Success

1.7/4

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

Trust Confidence

0.6/4

Confidence-adjusted reliability score that penalizes low evidence volume.

Abuse/Noise Resilience

3/4

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

2/4

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

Discovery Metadata

3/4

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

Registry Consistency

3/4

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

Installability

2/4

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

Session Semantics

0/4

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

Tool Surface Design

0/4

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

Result Shape Stability

0/4

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

OAuth Interop

0/4

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

2.5/4

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

Adoption Signal

3.6/4

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

0/4

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

Spec Recency

2/4

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

Session Resume

0/4

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

1/4

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

Utility Coverage

1/4

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

Advanced Capability Coverage

0/4

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

Connector Publishability

0/4

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

Tool Snapshot Churn

0/4

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

3/4

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

Official Registry Presence

3/4

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

4/4

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

Tool Capability Clarity

0/4

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

Destructive Operation Safety

1.5/4

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

Egress / SSRF Resilience

1.5/4

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

Execution / Sandbox Safety

1.5/4

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

Data Exfiltration Resilience

1/4

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

Least Privilege Scope

1.5/4

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

Secret Handling Hygiene

1.5/4

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

Supply Chain Signal

0.5/4

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

Input Sanitization Safety

0/4

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

Tool Namespace Clarity

0/4

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

Compatibility profiles

OpenAI Connectors

22.2

blocked

Connector URL: https://example.com/mcp
# No OAuth metadata detected.
# Server: github-api-evangelist/agnost-ai

Claude Desktop

16.7

blocked

{
  "mcpServers": {
    "agnost-ai": {
      "command": "npx",
      "args": ["mcp-remote", "https://example.com/mcp"]
    }
  }
}

Smithery

20.0

blocked

Requires a public remote MCP URL.; Tool discovery must succeed.; Initialize should work before execution.; Machine-readable failure semantics should be present.

smithery mcp add "https://example.com/mcp"

Generic Streamable HTTP

0.0

blocked

Requires an HTTP-native transport.; Requires a reachable remote MCP URL.; Initialize must succeed.; tools/list must succeed.; Transport behavior should match metadata.; Session behavior should be predictable.

curl -sS https://example.com/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
Critical	Ensure tools/list succeeds consistently	Tools discovery is the minimum viable contract for most MCP clients and directories.	Make tools/list succeed unauthenticated when possible, or document the auth flow in the server card. Playbook Make `tools/list` deterministic across repeated calls. Document or relax auth requirements for discovery routes. Check that tool names, descriptions, and schemas remain stable across deploys.
Critical	Make initialize deterministic and client-friendly	If initialize fails or requires undocumented auth, many MCP clients cannot connect.	Allow initialize to succeed consistently, or return a deterministic auth-required response with clear metadata. Playbook Allow `initialize` to succeed unauthenticated when possible. If auth is required, return a deterministic auth-required response and matching metadata. Retest against `your remote MCP URL` from a clean client session.
Critical	Respond to latest validation is failing	Core MCP flows did not validate successfully on the latest run.	Fix the failing checks first, then revalidate to confirm the recovery path. Playbook Fix the failing checks first. Review the latest incident feed and validation diff for the first regression. Revalidate once the remediation lands.
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.	Only send roots/list, sampling/createMessage, or elicitation/create requests while handling an active client-initiated request, never on idle sessions. Playbook Only send `roots/list`, `sampling/createMessage`, or `elicitation/create` requests while handling an active client-initiated request. Avoid emitting these requests on idle or newly-initialized sessions with no pending client request. Revalidate and confirm `request_association_probe` no longer returns `missing` or `warning`.
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.	Avoid removing tools, adding new required arguments, or changing outputSchema for tools already published to connector directories without a version bump. Playbook Avoid removing tools or adding new required arguments to existing tools without a major version bump. Avoid breaking changes to `outputSchema` for tools already published to connector directories. This check reads `no_historical_snapshot` on a server's first validation run -- that is expected, not itself a defect, and resolves after a second run.
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.
Medium	Adopt a current MCP protocol revision	Older protocol revisions reduce compatibility with newer clients and registry programs.	Advertise a current MCP protocol revision (2025-06-18 or later) in both the initialize response and the MCP-Protocol-Version header. Playbook Update the server's advertised protocol version to a current MCP revision (2025-06-18 or later). Return the negotiated version consistently in both the `initialize` response and the `MCP-Protocol-Version` header. Revalidate and confirm `protocol_version_probe` reports `ok`.
Medium	Close connector-publishing gaps	Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability.
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 Serve `/.well-known/openid-configuration` with `issuer`, `jwks_uri`, `authorization_endpoint`, and `token_endpoint`. List supported grant types in `grant_types_supported` and scopes in `scopes_supported`. Revalidate and confirm the `openid_configuration` check returns `ok`.
Medium	Raise Access & Protocol score	Connectivity, auth, and transport expectations for common clients.	Tighten auth discovery, session behavior, and transport metadata until remote clients can connect without guesswork.
Medium	Raise Adoption & Market score	Adoption clues and public evidence that the server is intended for external use.	Increase external documentation and directory coverage so users can discover and evaluate the server.
Medium	Raise Interface Quality score	How well the tool/resource interface communicates and behaves under automation.	Improve schemas, error contracts, and recovery messages so agents can reason about the surface automatically.
Medium	Reduce tool-surface churn	Frequent add/remove or output-shape drift makes published connectors and cached tool snapshots brittle.	Keep tool names, required arguments, and output schemas stable between deploys, and publish a changelog entry when they must change. Playbook Avoid changing tool names, required arguments, or output schemas between deploys unless the change is intentional. Publish a changelog entry when the tool surface changes so cached or frozen client snapshots can be reconciled. This check compares against the previous run, so it needs a second validation before it can report a stable baseline.
Medium	Repair prompts/list or stop advertising prompts	Prompt metadata should either work live or be removed from the advertised capability set.	Only advertise prompts if prompts/list works and prompt arguments are documented. Playbook Only advertise prompts that are actually accessible. Add prompt descriptions and argument docs. Run a live `prompts/list` check after any prompt changes.
Medium	Repair resources/list or stop advertising resources	Resource metadata should either work live or be removed from the advertised capability set.	Only advertise resources if resources/list works and resources expose stable URIs/types. Playbook Only advertise resources with stable URIs and read semantics. Add MIME/type hints where possible. Run a live `resources/list` and `resources/read` check after updates.
Medium	Support resumable HTTP sessions cleanly	Modern MCP clients increasingly expect resumable session behavior on streamable HTTP transports.	Persist session state keyed by Mcp-Session-Id and honor Last-Event-ID on GET reconnects so clients can resume a dropped Streamable HTTP session. Playbook Persist session state keyed by `Mcp-Session-Id` so a client can reconnect after a dropped connection. Honor `Last-Event-ID` on GET reconnects to replay missed SSE events instead of erroring. Revalidate and confirm `session_resume_probe` no longer returns `warning`.
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	Harden generic GET handling	Simple probe requests should not surface server instability or noisy failures.	Harden generic GET handlers around the origin of your remote MCP URL so incidental traffic does not produce noisy failures.
Low	Publish newer MCP capability signals	Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking.	Advertise only the advanced capabilities (roots, sampling, elicitation) you have actually implemented end to end in the initialize capabilities object. Playbook Add the capabilities you actually support (`roots`, `sampling`, `elicitation`) to the `capabilities` object returned from `initialize`. Only advertise a capability once the corresponding request/response flow is implemented end to end. Revalidate and confirm `advanced_capabilities_probe` reflects the updated capability set.
Low	Publish or reconcile the server in the official MCP registry	Official registry presence improves discovery confidence and cross-source consistency.

Point loss breakdown

Component	Current	Points missing
Transport Fidelity	0/4	-4.0
Tool Surface Design	0/4	-4.0
Tool Snapshot Churn	0/4	-4.0
Tool Namespace Clarity	0/4	-4.0
Tool Capability Clarity	0/4	-4.0
Session Semantics	0/4	-4.0
Session Resume	0/4	-4.0
Schema Completeness	0/4	-4.0
Result Shape Stability	0/4	-4.0
Recovery Semantics	0/4	-4.0
OAUTH Interop	0/4	-4.0
Input Sanitization Safety	0/4	-4.0

Validation diff

Score delta

-3.58

Summary changed

Tool delta

Prompt delta

Auth mode changed

Write surface expanded

Protocol regressed

Registry drift changed

Regressed checks: connector_publishability_probe

Improved checks: action_safety_probe, provenance_divergence_probe

Component	Previous	Latest	Delta
`execution_sandbox_safety_score`	4.0	1.5	-2.5
`advanced_capability_coverage_score`	2.0		-2.0
`data_exfiltration_resilience_score`	3.0	1.0	-2.0
`destructive_operation_safety_score`	3.0	1.5	-1.5
`egress_ssrf_resilience_score`	3.0	1.5	-1.5
`secret_handling_hygiene_score`	3.0	1.5	-1.5
`utility_coverage_score`	2.0	1.0	-1.0
`freshness_confidence_score`	2.5	3.0	0.5

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

Missing

Transport

unknown

Session header

Protocol header

Bad protocol response

n/a

DELETE teardown

n/a

Expired session retry

n/a

Last-Event-ID visible

Issues: none

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: none

Pagination

not detected

No nextCursor evidence.

Tasks

Missing

Advertised: no

Benchmark tasks

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

Registry & provenance divergence

Probe status

Direct official match

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

Latest validation is failing (critical)
Core MCP flows did not validate successfully on the latest run.

Aliases & registry graph

Identifier	Source	Canonical	Score
`github-api-evangelist/agnost-ai`	github_topic_registry	yes	11.2

Alias consolidation

Canonical identifier

github-api-evangelist/agnost-ai

Duplicate aliases

Registry sources

github_topic_registry

Remote URLs

none

Homepages

https://github.com/api-evangelist/agnost-ai

Source disagreements

Field	What differs	Observed values
No source disagreements detected.

Install snippets

Openai Connectors

Connector URL: https://example.com/mcp
# No OAuth metadata detected.
# Server: github-api-evangelist/agnost-ai

Claude Desktop

{
  "mcpServers": {
    "agnost-ai": {
      "command": "npx",
      "args": ["mcp-remote", "https://example.com/mcp"]
    }
  }
}

Smithery

smithery mcp add "https://example.com/mcp"

Generic Http

curl -sS https://example.com/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

No live tool surface captured yet.

Observed from the latest live validation against none. This is the target server surface, not Verify's own inspection tools.

Live capability counts

0 tools • 0 prompts • 0 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 github-api-evangelist/agnost-ai.

Direct machine links

JSON report • Compare this server • Verify MCP API

Latest validation evidence

Latest summary

Failing

Validation profile

remote_mcp

Started

Aug 04, 2026 07:58:35 PM UTC

Latency

6.9 ms

Failures

initialize no remote url
oauth_authorization_server no authorization server
oauth_protected_resource no remote url
openid_configuration no authorization server
probe_noise_resilience no remote url
server_card no server card url
tools_list no remote url

Checks

Check	Status	Latency	Evidence
`action_safety_probe`	OK	n/a	No high-risk write, destructive, or exec tools detected.
`advanced_capabilities_probe`	Missing	n/a	No advanced MCP capability signals detected.
`connector_publishability_probe`	Error	n/a	Publishability blockers: remote transport, initialize, tools list, protocol version, +4 more.
`connector_replay_probe`	Missing	n/a	No connector replay evidence recorded.
`determinism_probe`	Missing	n/a	no remote url
`initialize`	Missing	n/a	no remote url
`interactive_flow_probe`	Missing	n/a	Check completed
`oauth_authorization_server`	Missing	n/a	no authorization server
`oauth_protected_resource`	Missing	n/a	no remote url
`official_registry_probe`	Warning	n/a	Check completed
`openid_configuration`	Missing	n/a	no authorization server
`probe_noise_resilience`	Missing	n/a	no remote url
`prompt_get`	Missing	n/a	not advertised
`prompts_list`	Missing	n/a	no remote url
`protocol_version_probe`	Missing	n/a	No protocol version was advertised.
`provenance_divergence_probe`	OK	n/a	Check completed
`request_association_probe`	Missing	n/a	No request-association capabilities were advertised.
`resource_read`	Missing	n/a	not advertised
`resources_list`	Missing	n/a	no remote url
`server_card`	Missing	n/a	no server card url
`session_resume_probe`	Missing	n/a	no remote url
`step_up_auth_probe`	Missing	n/a	No OAuth or incremental-scope signals detected.
`tool_snapshot_probe`	Missing	n/a	no tools
`tools_list`	Missing	n/a	no remote url
`transport_compliance_probe`	Missing	n/a	Session header=no, protocol header=no, bad protocol=n/a.
`utility_coverage_probe`	Missing	n/a	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": 0,
          "capability_distribution": {},
          "destructive_tools": 0,
          "egress_tools": 0,
          "exec_tools": 0,
          "high_risk_tools": 0,
          "risk_distribution": {
            "critical": 0,
            "high": 0,
            "low": 0,
            "medium": 0
          },
          "secret_tools": 0,
          "tool_count": 0
        }
      },
      "latency_ms": null,
      "status": "ok"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": false,
          "resource_links": false,
          "resources": false,
          "roots": false,
          "sampling": false,
          "structured_outputs": false
        },
        "enabled": [],
        "enabled_count": 0,
        "initialize_capability_keys": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "remote_transport",
          "initialize",
          "tools_list",
          "protocol_version",
          "transport_compliance",
          "server_card",
          "tool_surface",
          "auth_flow"
        ],
        "criteria": {
          "action_safety": true,
          "auth_flow": false,
          "connector_replay": true,
          "initialize": false,
          "protocol_version": false,
          "remote_transport": false,
          "request_association": true,
          "server_card": false,
          "session_resume": true,
          "step_up_auth": true,
          "tool_surface": false,
          "tools_list": false,
          "transport_compliance": false
        },
        "high_risk_tools": 0,
        "tool_count": 0,
        "transport": null
      },
      "latency_ms": null,
      "status": "error"
    },
    "connector_replay_probe": {
      "details": {
        "reason": "no_tools"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "determinism_probe": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "initialize": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": false,
        "prompt_available": false,
        "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": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": false,
        "official_identifiers": [
          "ai.ai-akari/one-minute-akari",
          "ai.artidrop/artidrop",
          "ai.justpublish/just-publish",
          "ai.pimea/pimea",
          "ai.afmr/discovery",
          "ai.boolsai/directory",
          "ai.agenticfabricationnetwork/ufp",
          "ai.agenticshelf/graffeo",
          "ai.agentutility/mcp-model-router",
          "ac.tandem/docs-mcp"
        ],
        "official_peer_count": 10,
        "registry_source": "github_topic_registry"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "openid_configuration": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "probe_noise_resilience": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "prompt_get": {
      "details": {
        "reason": "not_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "prompts_list": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "protocol_version_probe": {
      "details": {
        "latest_known_version": "2025-11-25",
        "reason": "no_protocol_version",
        "validator_protocol_version": "2025-03-26"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "provenance_divergence_probe": {
      "details": {
        "direct_official_match": false,
        "drift_fields": [],
        "metadata_document_count": 1,
        "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": {
        "reason": "not_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "resources_list": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "server_card": {
      "details": {
        "reason": "no_server_card_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "session_resume_probe": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "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": {
        "reason": "no_tools"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tools_list": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "transport_compliance_probe": {
      "details": {
        "reason": "no_remote_url"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": null
        },
        "initialize_capability_keys": [],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": null,
          "probe_status": "missing"
        }
      },
      "latency_ms": null,
      "status": "missing"
    }
  },
  "failures": {
    "initialize": {
      "reason": "no_remote_url"
    },
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "reason": "no_remote_url"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "probe_noise_resilience": {
      "reason": "no_remote_url"
    },
    "server_card": {
      "reason": "no_server_card_url"
    },
    "tools_list": {
      "reason": "no_remote_url"
    }
  },
  "remote_url": null,
  "server_card_payload": null,
  "server_identifier": "github-api-evangelist/agnost-ai"
}

Known versions

No versions recorded.

Validation history

7 day score delta

n/a

30 day score delta

n/a

Recent healthy ratio

Freshness

5.0h

Timestamp	Status	Score	Latency
Aug 04, 2026 07:58:35 PM UTC	Failing	11.2	6.9 ms
Aug 04, 2026 10:57:47 AM UTC	Failing	14.8	5.7 ms
Aug 04, 2026 05:23:41 AM UTC	Failing	14.6	6.3 ms
Aug 03, 2026 10:03:24 PM UTC	Failing	14.4	4.7 ms
Aug 03, 2026 04:07:57 AM UTC	Failing	14.3	4.0 ms
Aug 02, 2026 08:43:29 PM UTC	Failing	12.9	4.3 ms

Validation timeline

Validated	Summary	Score	Protocol	Auth mode	Changes
Aug 04, 2026 07:58:35 PM UTC	Failing	11.2	unknown	unknown	none
Aug 04, 2026 10:57:47 AM UTC	Failing	14.8	unknown	unknown	none
Aug 04, 2026 05:23:41 AM UTC	Failing	14.6	unknown	unknown	none
Aug 03, 2026 10:03:24 PM UTC	Failing	14.4	unknown	unknown	none
Aug 03, 2026 04:07:57 AM UTC	Failing	14.3	unknown	unknown	none
Aug 02, 2026 08:43:29 PM UTC	Failing	12.9	unknown	unknown	none

Recent validation runs

Recent validation runs for this MCP server
Started	Status	Summary	Latency	Checks
Aug 04, 2026 07:58:35 PM UTC	Completed	Failing	6.9 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
Aug 04, 2026 10:57:47 AM UTC	Completed	Failing	5.7 ms
Aug 04, 2026 05:23:41 AM UTC	Completed	Failing	6.3 ms
Aug 03, 2026 10:03:24 PM UTC	Completed	Failing	4.7 ms
Aug 03, 2026 04:07:57 AM UTC	Completed	Failing	4.0 ms
Aug 02, 2026 08:43:29 PM UTC	Completed	Failing	4.3 ms