← Back to search
Search • Reliability • TrustOps • Docs • Pricing • Claim/Manage
github-agentage/find-mcp

agentage/find-mcp

Find MCP - stdio MCP client for the agentage MCP directory (catalog.agentage.io/mcp) - npx -y @agentage/find-mcp

JSON report • Policy • Badge metadata • History API •
• Global feed
DECISION SUMMARY
Production trust decision

Allow With Approval

Production readiness
Safe for evaluation
Score
60.4
Top 39.0% of 287 scored public servers. Live-validated, non-Failing servers with at least one inspected tool, ranked on the same publicly displayed score shown on this page.
Confidence
High
Based on evidence completeness, recency, and validation density.
Evidence age
11.7h old
Freshness: fresh. Snapshot trustsnap_60bee4a1864790d5.
Top risk drivers
  • Utility Coverage
  • Step Up Auth
  • Resource Contract
Recommended actions
  • Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.
  • Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata.
  • Publish /.well-known/oauth-authorization-server from your issuer and include registration endpoint when supported.
Next action
export policy, require approval for writes, add authenticated validation
write/admin actions need confirmation safeguards
Compare alternatives Export policy Open report JSON Dispute this assessment
Observed Attention
Low observed attention
AI discovery detected. This MCP server has recently appeared in AI-assisted discovery or evaluation traffic on Verify.
  • compare API 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.
Risks Compatibility Evidence Fix it Governance History Technical details
Status
Healthy
Score
60.4
Transport
streamable-http
Tools
3
Ownership
Unclaimed
Claim, revalidate, or manage this server
DISPUTE THIS ASSESSMENT

Dispute this assessment

If any published claim about this server -- its score, a risk flag, a capability classification, or its taxonomy -- is factually wrong, tell us what evidence shows and we will review it. This does not require claiming or verifying ownership of the server first.

Verify responds to disputes within 5 business days and resolves them within 15.

Dispute history

No disputes filed for this server.

Risks

Security posture
Tools analyzed
3
High-risk tools
0
Destructive tools
0
Exec tools
0
Egress tools
3
Secret tools
0
Bulk-access tools
0
Risk distribution
medium:3
Tool capability & risk inventory
ToolCapabilitiesRiskFindingsNotesEvidence
mcp_get read network Medium arbitrary network egress Safeguards hinted in metadata.
Schema & evidence 
{
  "annotations": {
    "destructiveHint": false,
    "openWorldHint": true,
    "readOnlyHint": true
  },
  "capabilities": [
    "read",
    "network"
  ],
  "input_schema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "slug": {
        "description": "The canonical slug of one server, taken verbatim from a mcp_search result. Catalog slugs are registry-derived and rarely match the plain product name (e.g. \"io-github-github-github-mcp-server\", not \"github\"), so prefer a slug from mcp_search. A plain name is accepted as a best-effort fallback: it resolves only when exactly one server matches, otherwise the error lists candidate slugs.",
        "minLength": 1,
        "type": "string"
      }
    },
    "required": [
      "slug"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress"
  ]
}
Dispute this classification
mcp_categories read network Medium arbitrary network egress Safeguards hinted in metadata.
Schema & evidence 
{
  "annotations": {
    "destructiveHint": false,
    "openWorldHint": true,
    "readOnlyHint": true
  },
  "capabilities": [
    "read",
    "network"
  ],
  "input_schema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {},
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress"
  ]
}
Dispute this classification
Write-action governance
Governance status
OK
Safe to publish
✓
Auth boundary
public_or_unclear
Blast radius
Low
High-risk tools
0
Confirmation signals
none
Safeguard count
3

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

ToolRiskFlagsSafeguards
No high-risk tools were detected on the latest run.
Recommended runtime policy
Recommended runtime policy
Allow with approval
Default policy stance (medium risk ceiling, write actions require approval, no OAuth requirement). Answers "what may an agent do right now" -- a separate question from production readiness, which answers "how suitable is this server for adoption." Customize via policy export.

No policy blockers under the default policy stance.

Action-controls diff
Snapshot changed
no
Disabled-by-default candidates
none
New actions
ActionRiskFlags
No newly added actions.
Changed actions
ActionChange typesRisk
No materially changed actions.
Critical alerts
High/critical-severity alerts
0
Production verdicts degrade quickly when high or critical-severity alerts are active.

Compatibility

Client readiness 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
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Step-up auth signals should be documented and connector-friendly.; OAuth interoperability should be strong.; OAuth is not configured, so this client cannot authenticate without additional setup.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.
Confidence: high (100.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initialize • OK
  • tools_list • OK
  • transport_compliance_probe • Warning
  • step_up_auth_probe • Missing
  • connector_replay_probe • OK — Frozen tool snapshots must survive refresh.
  • request_association_probe • Missing — Roots, sampling, and elicitation should stay request-scoped.
Client compatibility: Claude
Not client-compatible
OAuth is not configured, so this client cannot authenticate without additional setup.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully.
Confidence: high (100.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initialize • OK
  • tools_list • OK
  • transport_compliance_probe • Warning
Write-action publishing
Publishing allowed
Current write surface is bounded enough for cautious review with production policy controls.
Confidence: high (100.0)
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: high (100.0)
Evidence provenance
Winner: history
Supporting sources: history, live_validation
Disagreements: none
  • tool_snapshot_probe • OK
  • connector_replay_probe • OK
Client readiness gate details
ChatGPT custom connector
Not client-compatible
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Step-up auth signals should be documented and connector-friendly.; OAuth interoperability should be strong.; OAuth is not configured, so this client cannot authenticate without additional setup.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.
Remediation checklist
  • Add OAuth-based authentication for remote connector auth.
  • Support dynamic client registration (DCR) to simplify connector setup.
  • Document step-up auth requirements in a connector-friendly way.
  • Improve OAuth interoperability -- see the OAuth Interop score breakdown.
  • Configure OAuth for authenticated remote MCP access.
  • Satisfy OAuth, compatibility, and connector-refresh requirements before using the Messages API remote MCP path.
Claude remote MCP
Not client-compatible
OAuth is not configured, so this client cannot authenticate without additional setup.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully.
Remediation checklist
  • Configure OAuth for authenticated remote MCP access.
  • Satisfy OAuth, compatibility, and connector-refresh requirements before using the Messages API remote MCP path.
  • Resolve transport compliance issues before wider client rollout.
Write-safe publishing
Ready
No explicit blockers recorded.
Remediation checklist
  • No explicit blockers recorded.
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 (100.0)
Winning source: live_validation
Triggering alerts
  • instruction_tool_reference_mismatch • low • Server instructions name unavailable tools
Client verdict trace table
VerdictStatusChecksWinning sourceConflicts
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 publishability policy
Policy blocked
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Step-up auth signals should be documented and connector-friendly.; OAuth interoperability should be strong.; OAuth is not configured, so this client cannot authenticate without additional setup.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk. Technical compatibility is evaluated separately from this publishability policy.
  • Search Fetch Only: Yes
  • Write Actions Present: No
  • Oauth Configured: No
  • Admin Refresh Required: No
  • Safe For Company Knowledge: Yes
  • Safe For Messages Api Remote Mcp: No
Claude remote MCP publishability policy
Policy blocked
OAuth is not configured, so this client cannot authenticate without additional setup.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully. Technical compatibility is evaluated separately from this publishability policy.
  • Search Fetch Only: Yes
  • Write Actions Present: No
  • Oauth Configured: No
  • Admin Refresh Required: No
  • Safe For Company Knowledge: Yes
  • 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.; Step-up auth signals should be documented and connector-friendly.; OAuth interoperability should be strong.
  • remote_http_endpoint: Passes
  • oauth_discovery: Degraded
  • frozen_tool_snapshot_refresh: Passes
  • request_association: Not Assessed
Anthropic remote MCP fixture
Passes
Remote MCP transport and discovery assumptions are satisfied.
  • remote_transport: Passes
  • tool_discovery: Passes
  • auth_connect: Passes
  • safe_write_review: Passes
Recommended for
Smithery
Smithery is marked compatible with score 100.
Generic Streamable HTTP
Generic Streamable HTTP is marked compatible with score 100.

Evidence

Current trust snapshot
Snapshot ID
trustsnap_60bee4a1864790d5
Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.
Trust evaluated
Aug 15, 2026 03:44:35 PM UTC
Evidence revision: b90045cad8a405d0de6a3d15 • materialization: complete
Last validated
Aug 15, 2026 04:01:13 AM UTC
Age: 11.72h • evidence age tier: Verified in last 24h • display score: 60.42

Canonical machine links

Compare index
/compare.json
Compare API
/v1/compare?server=github-agentage%2Ffind-mcp
Trust summary
/v1/servers/github-agentage/find-mcp/trust-summary
Report JSON
/v1/servers/github-agentage/find-mcp/report
Policy export
/v1/servers/github-agentage/find-mcp/policy
Badge metadata
/v1/servers/github-agentage/find-mcp/badge
Ledger evidence
/v1/servers/github-agentage/find-mcp/ledger
Human compare URL
/compare?server=github-agentage%2Ffind-mcp
Evidence confidence
Confidence score
100.0
Based on 20 recent validations, 13 captured checks, and validation age of 11.7 hours.
Live checks captured
13
More direct checks increase trust in the current verdict.
Validation age
11.7h
Lower age means fresher evidence.
Latest validation evidence
Latest summary
Healthy
Validation profile
remote_mcp
Started
Aug 15, 2026 04:01:05 AM UTC
Latency
7442.0 ms

Failures

  • oauth_authorization_server no authorization server
  • oauth_protected_resource Non-MCP content type: text/html; charset=utf-8
  • openid_configuration no authorization server
  • server_card Non-MCP content type: text/html; charset=utf-8

Checks

CheckStatusLatencyEvidence
action_safety_probe OK n/a 3 egress-capable tool(s); no clear auth boundary; safeguards=3; confirmation=none.
advanced_capabilities_probe Warning n/a Only 1 capability signal(s): structured outputs.
connector_publishability_probe Warning n/a Publishability blockers: protocol version, session resume, step up auth, transport compliance, +2 more.
connector_replay_probe OK n/a Backward compatible with no breaking tool-surface changes.
determinism_probe OK 353.2 ms Check completed
initialize OK 1535.1 ms Protocol 2025-03-26
instruction_tool_reference_probe Warning n/a Check completed
interactive_flow_probe Missing n/a Check completed
oauth_authorization_server Missing n/a no authorization server
oauth_protected_resource Error 1446.8 ms Non-MCP content type: text/html; charset=utf-8
official_registry_probe Missing n/a Check completed
openid_configuration Missing n/a no authorization server
probe_noise_resilience OK 1363.8 ms Fetched https://catalog.agentage.io/robots.txt
prompt_get Missing n/a not advertised
prompts_list Missing 889.9 ms not supported
protocol_version_probe Warning n/a Claims 2025-03-26; 2 release(s) behind 2025-11-25.
provenance_divergence_probe Not_Assessed 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 135.2 ms not supported
schema_divergence_probe Missing n/a no server card tools
server_card Error 572.1 ms Non-MCP content type: text/html; charset=utf-8
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 OK n/a Check completed
tools_list OK 396.6 ms 3 tool(s) exposed
transport_compliance_probe Warning 135.1 ms Issues: missing session id, missing protocol header (bad protocol=400).
utility_coverage_probe Missing 136.6 ms No completions evidence; no pagination evidence; tasks missing.
Known versions
  • No versions recorded.
Public server reputation
Validation success 7d
1.0
Validation success 30d
1.0
Mean time to recover
n/a
Breaking diffs 30d
1
Registry drift frequency 30d
0
Snapshot changes 30d
1
Benchmark tasks
Benchmark taskStatusEvidence
Discover tools Passes
  • initialize • OK
  • tools_list • OK
Read-only fetch flow Likely to fail
  • resource_read • Missing
  • read_only_tool_surface • Missing
OAuth-required connect Degraded
  • oauth_protected_resource • Error
  • step_up_auth_probe • Missing
Safe write flow with confirmation Passes
  • action_safety_probe • OK
Utility coverage
Probe status
Missing
Completions
not detected
Completion probe target: none
Pagination
not detected
No nextCursor evidence.
Tasks
Missing
Advertised: no
Tool snapshot diff & changelog
Snapshot changed
no
Added tools
none
Removed tools
none
Required-argument changes
ToolAdded required argsRemoved required args
No required-argument changes detected.
Output-schema drift
ToolPrevious propertiesLatest properties
No output-schema drift detected.
Validation diff
Score delta
0
Summary changed
no
Tool delta
0
Prompt delta
0
Auth mode changed
no
Write surface expanded
no
Protocol regressed
no
Registry drift changed
no

Regressed checks: none

Improved checks: none

Newly assessed dimensions: none

No longer assessed dimensions: none

ComponentPreviousLatestDelta
No component deltas between the latest two runs.
Registry & provenance divergence
Probe status
Not_Assessed
Assessment
Not assessed
probe_not_assessed
Cross-registry alias disagreements
none
Active alerts
  • Server instructions name unavailable tools (low)
    Initialize instructions reference tools not present in tools/list: it
Aliases & registry graph
IdentifierSourceCanonicalIdentity evidenceScore
github-agentage/find-mcp github_topic_registry yes canonical 60.4
Alias consolidation

Strong alias identity requires matching remote URL, server-card URL, repository slug, or explicit registry cross-reference; shared provider namespace alone is not identity.

Canonical identifier
github-agentage/find-mcp
Duplicate aliases
0
Registry sources
github_topic_registry
MCP endpoints
Directory listings
none
Homepages
Source disagreements
FieldWhat differsObserved values
No source disagreements detected.

Fix it

Why this score?
Access & Protocol
24/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
31/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
23/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
23/24
Operational stability, consistency, and trustworthiness over time.
Discovery & Governance
11/28
How well the server is documented, listed, and governed in public registries.
Adoption & Market
4/8
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
2/4
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
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
3/4
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
4/4
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
0/4
Quality of prompt metadata, argument shape, and prompt discoverability for clients.
Resource Contract
0/4
How completely resources and resource templates describe URIs, types, and usage shape.
Discovery Metadata
2/4
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
4/4
Naming clarity, schema ergonomics, and parameter complexity across the tool surface.
Result Shape Stability
4/4
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
3/4
Versioning, update recency, and historical validation cadence that indicate active stewardship.
Adoption Signal
2/4
Directory presence and distribution clues that suggest the server is intended for external use.
Freshness Confidence
4/4
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
2/4
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
0/4
Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.
Transport Compliance
2/4
Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.
Utility Coverage
0/4
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
2/4
How ready the server looks for client catalogs and managed connector programs.
Tool Snapshot Churn
4/4
Stability of the tool surface across recent validations, including add/remove and output-shape drift.
Connector Replay
4/4
Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.
Request Association
0/4
Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.
Interactive Flow Safety
0/4
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
2/4
Whether the server appears directly or indirectly in the official MCP registry.
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
1/4
Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.
Execution / Sandbox Safety
4/4
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
3/4
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
0/4
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.

1 component(s) not assessed for this run: Provenance Divergence

Experimental candidate components
Personal Data Exposure
8.5
Experimental candidate, weight 0. Export and bulk-access evidence only; no impact on totals, verdicts, rankings, or gates.
Actionable remediation
SeverityRemediationWhy it mattersRecommended action
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 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 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.
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. Resolve every blocker named by connector_publishability_probe, then rerun it before submitting or refreshing a connector listing.
Playbook
  • Review the blockers and failed criteria recorded by connector_publishability_probe.
  • Correct the identified transport, authentication, server-card, or tool-stability gaps.
  • Revalidate and require the probe to report no blockers before publishing the connector.
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 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 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 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. Create or update the official MCP registry entry with the canonical MCP endpoint and matching repository metadata, then rerun official_registry_probe.
Playbook
  • Locate or create the canonical entry in the official MCP registry.
  • Publish the live MCP endpoint and reconcile its repository and homepage metadata.
  • Revalidate and confirm official_registry_probe recognizes the reconciled entry.
Low Remove stale tool names from server instructions Initialize instructions explicitly reference tools that tools/list does not expose. Update initialize instructions so every explicitly named tool exists in tools/list.
Playbook
  • Compare the initialize result's instructions field with the current tools/list names.
  • Rename the explicit reference or restore the missing tool.
  • Revalidate and confirm instruction_tool_reference_probe reports ok.
Point loss breakdown
ComponentCurrentPoints missing
Utility Coverage 0/4 -4.0
Step-Up Auth 0/4 -4.0
Resource Contract 0/4 -4.0
Request Association 0/4 -4.0
Recovery Semantics 0/4 -4.0
Prompt Contract 0/4 -4.0
OAuth Interop 0/4 -4.0
Interactive Flow Safety 0/4 -4.0
Supply Chain Signal 0/4 -4.0
Advanced Capability Coverage 0/4 -4.0
Egress / SSRF Resilience 1/4 -3.0
Transport Compliance 2/4 -2.0
Technical compatibility profiles

These scores measure technical client compatibility only. Client publishability and production readiness are evaluated separately against policy, transport, and write-surface blockers.

OpenAI Connectors
55.6
Technical review required (5 of 9 requirements met)
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Step-up auth signals should be documented and connector-friendly.; OAuth interoperability should be strong.
Connector URL: https://catalog.agentage.io/mcp
# No OAuth metadata detected.
# Server: github-agentage/find-mcp
Claude Desktop
100.0
Technically compatible (6 of 6 requirements met)
No technical compatibility criteria are currently unmet.
{
  "mcpServers": {
    "find-mcp": {
      "command": "npx",
      "args": ["mcp-remote", "https://catalog.agentage.io/mcp"]
    }
  }
}
Smithery
100.0
Technically compatible (5 of 5 requirements met)
No technical compatibility criteria are currently unmet.
smithery mcp add "https://catalog.agentage.io/mcp"
Generic Streamable HTTP
100.0
Technically compatible (6 of 6 requirements met)
No technical compatibility criteria are currently unmet.
curl -sS https://catalog.agentage.io/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"}}}'

Governance

MCP TrustOps

TrustOps turns this report into operational controls: validation targets and 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 evidence-age limit (a runtime constraint, distinct from the public 24h freshness window and from a plan's validation target/SLA): 168.0h • confidence-weighted score (display score discounted for evidence age and confidence -- an internal TrustOps input, not the public score): 60.4 • score suppressed after the 30-day display limit: ✕
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 Evidence-age policy 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
DeploymentStatusEndpointRelease
No hosted runtime deployments yet.
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
Install snippets
Openai Connectors
Connector URL: https://catalog.agentage.io/mcp
# No OAuth metadata detected.
# Server: github-agentage/find-mcp
Claude Desktop
{
  "mcpServers": {
    "find-mcp": {
      "command": "npx",
      "args": ["mcp-remote", "https://catalog.agentage.io/mcp"]
    }
  }
}
Smithery
smithery mcp add "https://catalog.agentage.io/mcp"
Generic Http
curl -sS https://catalog.agentage.io/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
mcp_search mcp_get mcp_categories
Observed from the latest live validation against https://catalog.agentage.io/mcp. This is the target server surface, not Verify's own inspection tools.
Live capability counts
3 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-agentage/find-mcp.
Direct machine links
JSON report • Compare this server • Verify MCP API

History

Validation history
7 day score delta
n/a
30 day score delta
n/a
Recent healthy ratio
100%
Freshness
11.7h
TimestampStatusScoreLatencyTools
Aug 15, 2026 04:01:13 AM UTC Healthy 60.4 7442.0 ms 3
Aug 15, 2026 03:58:55 AM UTC Healthy 60.4 5970.7 ms 3
Aug 14, 2026 03:52:34 PM UTC Healthy 60.4 2552.6 ms 3
Aug 14, 2026 03:21:04 AM UTC Healthy 55.7 2776.8 ms 3
Aug 13, 2026 08:37:43 PM UTC Healthy 60.4 2751.5 ms 3
Aug 13, 2026 08:31:23 AM UTC Healthy 60.4 2824.4 ms 3
Aug 12, 2026 08:10:54 PM UTC Healthy 60.9 2620.1 ms 3
Aug 12, 2026 07:58:06 AM UTC Healthy 60.9 2801.3 ms 3
Aug 11, 2026 07:29:02 PM UTC Healthy 60.9 2628.8 ms 3
Aug 11, 2026 07:07:48 AM UTC Healthy 60.9 2795.5 ms 3
Validation timeline
ValidatedSummaryScoreProtocolAuth modeToolsHigh-risk toolsChanges
Aug 15, 2026 04:01:13 AM UTC Healthy 60.4 2025-03-26 public 3 0 none
Aug 15, 2026 03:58:55 AM UTC Healthy 60.4 2025-03-26 public 3 0 none
Aug 14, 2026 03:52:34 PM UTC Healthy 60.4 2025-03-26 public 3 0 none
Aug 14, 2026 03:21:04 AM UTC Healthy 55.7 2025-03-26 public 3 0 tool_snapshot_changed
Aug 13, 2026 08:37:43 PM UTC Healthy 60.4 2025-03-26 public 3 0 none
Aug 13, 2026 08:31:23 AM UTC Healthy 60.4 2025-03-26 public 3 0 none
Aug 12, 2026 08:10:54 PM UTC Healthy 60.9 2025-03-26 public 3 0 none
Aug 12, 2026 07:58:06 AM UTC Healthy 60.9 2025-03-26 public 3 0 none
Aug 11, 2026 07:29:02 PM UTC Healthy 60.9 2025-03-26 public 3 0 none
Aug 11, 2026 07:07:48 AM UTC Healthy 60.9 2025-03-26 public 3 0 none
Recent validation runs
Recent validation runs for this MCP server
StartedStatusSummaryLatencyChecks
Aug 15, 2026 04:01:05 AM UTC Completed Healthy 7442.0 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, instruction_tool_reference_probe, 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 15, 2026 03:58:49 AM UTC Completed Healthy 5970.7 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, instruction_tool_reference_probe, 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 14, 2026 03:52:32 PM UTC Completed Healthy 2552.6 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, instruction_tool_reference_probe, 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 14, 2026 03:21:01 AM UTC Completed Healthy 2776.8 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, instruction_tool_reference_probe, 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 13, 2026 08:37:40 PM UTC Completed Healthy 2751.5 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 13, 2026 08:31:20 AM UTC Completed Healthy 2824.4 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 12, 2026 08:10:51 PM UTC Completed Healthy 2620.1 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 12, 2026 07:58:03 AM UTC Completed Healthy 2801.3 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 11, 2026 07:28:59 PM UTC Completed Healthy 2628.8 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 11, 2026 07:07:45 AM UTC Completed Healthy 2795.5 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Incident & change feed
TimestampEventDetails
Aug 15, 2026 04:01:13 AM UTC Latest validation: healthy Score 60.4 with status healthy.
Aug 14, 2026 03:52:34 PM UTC Score changed Score delta +4.7 versus the previous run.
Aug 05, 2026 11:02:33 AM UTC Score corrected (post-1.0.503 remediation, R1 zero-anchoring) Prior: 69.18. Corrected: 66.94.

Technical details

Raw evidence view
Show raw JSON evidence 
{
  "checks": {
    "action_safety_probe": {
      "details": {
        "auth_present": false,
        "confirmation_signals": [],
        "reason": null,
        "safeguard_count": 3,
        "summary": {
          "annotation_conflict_tools": 0,
          "bulk_access_tools": 0,
          "capability_distribution": {
            "network": 3,
            "read": 3
          },
          "declared_non_read_only_tools": 0,
          "destructive_tools": 0,
          "egress_tools": 3,
          "exec_tools": 0,
          "has_mutating_capability": false,
          "has_non_read_capability": false,
          "high_risk_tools": 0,
          "risk_distribution": {
            "critical": 0,
            "high": 0,
            "low": 0,
            "medium": 3
          },
          "secret_tools": 0,
          "tool_count": 3
        }
      },
      "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": true
        },
        "enabled": [
          "structured_outputs"
        ],
        "enabled_count": 1,
        "initialize_capability_keys": [
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "protocol_version",
          "session_resume",
          "step_up_auth",
          "transport_compliance",
          "request_association",
          "server_card"
        ],
        "criteria": {
          "action_safety": true,
          "auth_flow": true,
          "connector_replay": true,
          "initialize": true,
          "protocol_version": false,
          "remote_transport": true,
          "request_association": false,
          "server_card": false,
          "session_resume": false,
          "step_up_auth": false,
          "tool_surface": true,
          "tools_list": true,
          "transport_compliance": false
        },
        "high_risk_tools": 0,
        "tool_count": 3,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_replay_probe": {
      "details": {
        "added_tools": [],
        "additive_output_changes": [],
        "backward_compatible": true,
        "output_breaks": [],
        "removed_tools": [],
        "required_arg_breaks": [],
        "would_break_after_refresh": false
      },
      "latency_ms": null,
      "status": "ok"
    },
    "determinism_probe": {
      "details": {
        "attempts": 2,
        "baseline_signature": "d29983ba54afb200c25a74cda0c05b066a25ecc2c751617ad28752221fb6c32d",
        "errors": [],
        "matches": 2,
        "stable_ratio": 1.0,
        "successful": 2
      },
      "latency_ms": 353.2,
      "status": "ok"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "ratelimit-limit": "60",
          "ratelimit-remaining": "59",
          "ratelimit-reset": "60",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 1,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "tools": {
                "listChanged": true
              }
            },
            "instructions": "A public directory of Model Context Protocol (MCP) servers, crawled from the official registry. Use it to discover, compare, and look up MCP servers on request (\"is there an MCP for X\", \"which MCP server does Y\"). mcp_search finds servers by keyword and filters; mcp_get returns one server's full packages, tools, and install command by slug; mcp_categories lists the category/language/license values you can filter on. Read-only - it never installs or runs anything.",
            "protocolVersion": "2025-03-26",
            "serverInfo": {
              "name": "find-mcp",
              "title": "Find MCP - Agentage MCP Directory",
              "version": "0.1.0",
              "websiteUrl": "https://catalog.agentage.io/mcp"
            }
          }
        },
        "url": "https://catalog.agentage.io/mcp"
      },
      "latency_ms": 1535.07,
      "status": "ok"
    },
    "instruction_tool_reference_probe": {
      "details": {
        "missing_tools": [
          "it"
        ],
        "observed_tool_count": 3,
        "referenced_tools": [
          "it"
        ]
      },
      "latency_ms": null,
      "status": "warning"
    },
    "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": {
        "error": "Non-MCP content type: text/html; charset=utf-8",
        "non_mcp_content_type": "text/html; charset=utf-8",
        "url": "https://catalog.agentage.io/.well-known/oauth-protected-resource"
      },
      "latency_ms": 1446.82,
      "status": "error"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": false,
        "official_peer_count": 0,
        "registry_source": "github_topic_registry"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "openid_configuration": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "probe_noise_resilience": {
      "details": {
        "consent_error": null,
        "headers": {
          "content-type": "text/plain"
        },
        "http_status": 200,
        "url": "https://catalog.agentage.io/robots.txt",
        "validation_disallowed": false
      },
      "latency_ms": 1363.78,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "reason": "not_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "ratelimit-limit": "60",
          "ratelimit-remaining": "58",
          "ratelimit-reset": "60",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "error": {
            "code": -32601,
            "message": "Method not found"
          },
          "id": 3,
          "jsonrpc": "2.0"
        },
        "reason": "not_supported",
        "url": "https://catalog.agentage.io/mcp"
      },
      "latency_ms": 889.9,
      "status": "missing"
    },
    "protocol_version_probe": {
      "details": {
        "claimed_version": "2025-03-26",
        "lag_days": 244,
        "latest_known_version": "2025-11-25",
        "releases_behind": 2,
        "validator_protocol_version": "2025-03-26"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "provenance_divergence_probe": {
      "details": {
        "comparable_field_count": 0,
        "compared_fields": [
          "title",
          "version",
          "homepage",
          "repository"
        ],
        "direct_official_match": false,
        "drift_fields": [],
        "metadata_document_count": 1,
        "readable_sources": [],
        "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": "not_assessed"
    },
    "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": {
        "headers": {
          "content-type": "application/json",
          "ratelimit-limit": "60",
          "ratelimit-remaining": "58",
          "ratelimit-reset": "59",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "error": {
            "code": -32601,
            "message": "Method not found"
          },
          "id": 5,
          "jsonrpc": "2.0"
        },
        "reason": "not_supported",
        "url": "https://catalog.agentage.io/mcp"
      },
      "latency_ms": 135.16,
      "status": "missing"
    },
    "schema_divergence_probe": {
      "details": {
        "auth_scheme_mismatch": false,
        "card_server_name": null,
        "card_server_version": null,
        "compared_dimensions": [
          "server_name",
          "server_version",
          "declared_vs_observed_auth",
          "tool_membership",
          "parameter_names",
          "required_parameters",
          "parameter_types",
          "output_schema_presence"
        ],
        "compared_tool_count": 0,
        "live_server_name": "find-mcp",
        "live_server_version": "0.1.0",
        "reason": "no_server_card_tools",
        "server_name_mismatch": false,
        "server_version_mismatch": false
      },
      "latency_ms": null,
      "status": "missing"
    },
    "server_card": {
      "details": {
        "error": "Non-MCP content type: text/html; charset=utf-8",
        "non_mcp_content_type": "text/html; charset=utf-8",
        "url": "https://catalog.agentage.io/.well-known/mcp/server-card.json"
      },
      "latency_ms": 572.07,
      "status": "error"
    },
    "session_resume_probe": {
      "details": {
        "protocol_version": "2025-03-26",
        "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": {
        "added": [],
        "changed_outputs": [],
        "current_tool_count": 3,
        "previous_tool_count": 3,
        "removed": [],
        "similarity": 1.0
      },
      "latency_ms": null,
      "status": "ok"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "ratelimit-limit": "60",
          "ratelimit-remaining": "59",
          "ratelimit-reset": "60",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "_meta": {
              "cacheScope": "public",
              "ttlMs": 21600000
            },
            "cacheScope": "public",
            "tools": [
              {
                "annotations": {
                  "destructiveHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": true
                },
                "description": "Search the agentage MCP directory - a public catalog of Model Context Protocol servers crawled from the official registry - for servers matching a keyword, optionally narrowed by type, category, language, or license. Use this FIRST whenever the user wants to discover, find, compare, or pick an MCP server (\"is there an MCP for X\", \"which MCP servers do Y\"). Results are ranked by text relevance to the query first, then by popularity, so the best match is on top. Returns a page of lean cards (slug, title, description, category, transport, match_score - text relevance the ranking is based on, details_url). To read one server's full packages, tools, and install command, call mcp_get with the slug from a result; open a card's details_url for the human detail page. Valid category, language, and license values come from the mcp_categories tool, not from guesswork - call it before filtering and pass its labels verbatim, or the call is rejected. Read-only - never installs or runs anything.",
                "execution": {
                  "taskSupport": "forbidden"
                },
                "inputSchema": {
                  "$schema": "http://json-schema.org/draft-07/schema#",
                  "properties": {
                    "category": {
                      "description": "Optional. Restrict to one category label. Valid values come from the mcp_categories tool - call it to get the exact labels (with counts) and pass one verbatim; anything else is rejected. Omit for no category filter.",
                      "enum": [
                        "Development & Coding",
                        "Data & Databases",
                        "Search & Web",
                        "AI & Machine Learning",
                        "Productivity & Docs",
                        "Communication & Messaging",
                        "Cloud & DevOps",
                        "Finance & Crypto",
                        "Security",
                        "Media & Design",
                        "Browser & Automation",
                        "Knowledge & Memory",
                        "Commerce & Marketing",
                        "Other"
                      ],
                      "type": "string"
                    },
                    "language": {
                      "description": "Optional. Restrict to a repository language (e.g. \"TypeScript\", \"Python\"). Exact, case-sensitive; call mcp_categories for valid values. Omit for no language filter.",
                      "maxLength": 80,
                      "minLength": 1,
                      "type": "string"
                    },
                    "license": {
                      "description": "Optional. Restrict to a license, given either as an SPDX id (\"MIT\", \"Apache-2.0\") or as the full name mcp_categories lists (\"MIT License\"). Omit for no license filter.",
                      "maxLength": 80,
                      "minLength": 1,
                      "type": "string"
                    },
                    "limit": {
                      "description": "Optional. Results per page; defaults to 20, capped at 50.",
                      "maximum": 50,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "page": {
                      "description": "Optional. 1-based page number; defaults to 1. Use pagination.total_pages to page.",
                      "maximum": 9007199254740991,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "What to search for - a keyword, product, capability, or server name (e.g. \"github\", \"postgres\", \"web search\"). Matched across names, titles, and descriptions. Prefer a single distinctive term over a long phrase.",
                      "minLength": 1,
                      "type": "string"
                    },
                    "type": {
                      "description": "Optional. Restrict to one distribution type: npm | pypi | oci | mcpb | nuget, or \"remote\" for hosted (HTTP) servers. Omit to search every type.",
                      "enum": [
                        "npm",
                        "pypi",
                        "oci",
                        "mcpb",
                        "nuget",
                        "remote"
                      ],
                      "type": "string"
                    }
                  },
                  "required": [
                    "query"
                  ],
                  "type": "object"
                },
                "name": "mcp_search",
                "outputSchema": {
                  "$schema": "http://json-schema.org/draft-07/schema#",
                  "additionalProperties": false,
                  "properties": {
                    "pagination": {
                      "additionalProperties": false,
                      "properties": {
                        "has_more": {
                          "type": "boolean"
                        },
                        "limit": {
                          "type": "number"
                        },
                        "page": {
                          "type": "number"
                        },
                        "total": {
                          "type": "number"
                        },
                        "total_pages": {
                          "type": "number"
                        }
                      },
                      "required": [
                        "page",
                        "limit",
                        "total",
                        "total_pages",
                        "has_more"
                      ],
                      "type": "object"
                    },
                    "query": {
                      "description": "The query the backend actually ran",
                      "type": "string"
                    },
                    "results": {
                      "items": {
                        "additionalProperties": false,
                        "properties": {
                          "category": {
                            "description": "AI-assigned category labels",
                            "items": {
                              "type": "string"
                            },
                            "type": "array"
                          },
                          "description": {
                            "type": "string"
                          },
                          "details_url": {
                            "description": "Human detail page for this server - open it for more information",
                            "type": "string"
                          },
                          "is_official": {
                            "description": "Present in the official MCP registry",
                            "type": "boolean"
                          },
                          "language": {
                            "description": "Primary repository language, when known",
                            "type": "string"
                          },
                          "license": {
                            "description": "License name, when known, e.g. \"MIT License\"",
                            "type": "string"
                          },
                          "match_score": {
                            "description": "Text relevance the ranking is based on; higher is a closer match to the query",
                            "type": "number"
                          },
                          "slug": {
                            "description": "Stable id - pass verbatim to mcp_get for full details",
                            "type": "string"
                          },
                          "title": {
                            "description": "Human-readable server name",
                            "type": "string"
                          },
                          "tool_count": {
                            "description": "Number of MCP tools the server exposes, when known",
                            "type": "number"
                          },
                          "transport_types": {
                            "description": "How the server ships/runs, e.g. [\"npm\"], [\"remote\"]",
                            "items": {
                              "type": "string"
                            },
                            "type": "array"
                          }
                        },
                        "required": [
                          "slug",
                          "title",
                          "description",
                          "category",
                          "is_official",
                          "transport_types",
                          "details_url"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    }
                  },
                  "required": [
                    "results",
                    "pagination",
                    "query"
                  ],
                  "type": "object"
                },
                "title": "Search the MCP directory"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": true
                },
                "description": "Fetch the complete record for ONE MCP server in the agentage directory by its canonical slug: full description, categories, the packages and remote endpoints it ships, the tools it exposes, a ready-to-run install command, and a README excerpt. Use this after mcp_search to get the depth a result card omits - pass a slug exactly as returned by mcp_search. Slugs are canonical and registry-derived (\"io-github-github-github-mcp-server\"), NOT the plain product name (\"github\"); if you pass a plain name anyway it is resolved by search as a fallback - a single confident match returns that server (with `resolved_from` set), anything else returns an error naming the candidate slugs to retry with. No slug yet? call mcp_search first. Read-only.",
                "execution": {
                  "taskSupport": "forbidden"
                },
                "inputSchema": {
                  "$schema": "http://json-schema.org/draft-07/schema#",
                  "properties": {
                    "slug": {
                      "description": "The canonical slug of one server, taken verbatim from a mcp_search result. Catalog slugs are registry-derived and rarely match the plain product name (e.g. \"io-github-github-github-mcp-server\", not \"github\"), so prefer a slug from mcp_search. A plain name is accepted as a best-effort fallback: it resolves only when exactly one server matches, otherwise the error lists candidate slugs.",
                      "minLength": 1,
                      "type": "string"
                    }
                  },
                  "required": [
                    "slug"
                  ],
                  "type": "object"
                },
                "name": "mcp_get",
                "outputSchema": {
                  "$schema": "http://json-schema.org/draft-07/schema#",
                  "additionalProperties": false,
                  "properties": {
                    "category": {
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "description": {
                      "type": "string"
                    },
                    "details_url": {
                      "description": "Human detail page for this server - open it for more information",
                      "type": "string"
                    },
                    "install": {
                      "additionalProperties": false,
                      "description": "The recommended way to run this server, derived from its first package/remote",
                      "properties": {
                        "command": {
                          "description": "A suggested command or connection hint to run the server",
                          "type": "string"
                        },
                        "identifier": {
                          "type": "string"
                        },
                        "registry_type": {
                          "type": "string"
                        }
                      },
                      "required": [
                        "registry_type",
                        "identifier",
                        "command"
                      ],
                      "type": "object"
                    },
                    "is_official": {
                      "type": "boolean"
                    },
                    "language": {
                      "type": "string"
                    },
                    "license": {
                      "type": "string"
                    },
                    "name": {
                      "type": "string"
                    },
                    "packages": {
                      "items": {
                        "additionalProperties": false,
                        "properties": {
                          "environment_variables": {
                            "description": "Env vars the server reads, for setup",
                            "items": {
                              "additionalProperties": false,
                              "properties": {
                                "description": {
                                  "type": "string"
                                },
                                "name": {
                                  "type": "string"
                                },
                                "required": {
                                  "type": "boolean"
                                },
                                "secret": {
                                  "type": "boolean"
                                }
                              },
                              "required": [
                                "name"
                              ],
                              "type": "object"
                            },
                            "type": "array"
                          },
                          "identifier": {
                            "description": "Package id in that registry",
                            "type": "string"
                          },
                          "registry_type": {
                            "description": "npm | pypi | oci | mcpb | nuget",
                            "type": "string"
                          },
                          "runtime_hint": {
                            "type": "string"
                          },
                          "transport_type": {
                            "description": "stdio | streamable-http | sse, when declared",
                            "type": "string"
                          },
                          "version": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "registry_type",
                          "identifier"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "readme_excerpt": {
                      "description": "First ~2000 chars of the README; open details_url for the full document",
                      "type": "string"
                    },
                    "remotes": {
                      "items": {
                        "additionalProperties": false,
                        "properties": {
                          "type": {
                            "description": "e.g. streamable-http, sse",
                            "type": "string"
                          },
                          "url": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "type",
                          "url"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "resolved_from": {
                      "description": "Present only when the requested slug was not canonical and was resolved by name; this is what you asked for - use `slug` from now on",
                      "type": "string"
                    },
                    "slug": {
                      "type": "string"
                    },
                    "title": {
                      "type": "string"
                    },
                    "tools": {
                      "description": "The MCP tools this server exposes, from its live tools/list",
                      "items": {
                        "additionalProperties": false,
                        "properties": {
                          "description": {
                            "type": "string"
                          },
                          "name": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "name"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "transport_types": {
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    }
                  },
                  "required": [
                    "slug",
                    "name",
                    "title",
                    "description",
                    "category",
                    "is_official",
                    "transport_types",
                    "tools",
                    "packages",
                    "remotes",
                    "details_url"
                  ],
                  "type": "object"
                },
                "title": "Get one MCP server"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": true
                },
                "description": "List the directory's available filter values - every category, language, and license, each with how many servers carry it. Call this BEFORE mcp_search when you intend to filter, so you pass exact, existing values for the type/category/language/license arguments instead of guessing. Takes no input. Read-only.",
                "execution": {
                  "taskSupport": "forbidden"
                },
                "inputSchema": {
                  "$schema": "http://json-schema.org/draft-07/schema#",
                  "properties": {},
                  "type": "object"
                },
                "name": "mcp_categories",
                "outputSchema": {
                  "$schema": "http://json-schema.org/draft-07/schema#",
                  "additionalProperties": false,
                  "properties": {
                    "categories": {
                      "description": "Category labels and how many servers carry each",
                      "items": {
                        "additionalProperties": false,
                        "properties": {
                          "count": {
                            "type": "number"
                          },
                          "name": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "name",
                          "count"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "languages": {
                      "description": "Repository languages and their server counts",
                      "items": {
                        "additionalProperties": false,
                        "properties": {
                          "count": {
                            "type": "number"
                          },
                          "name": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "name",
                          "count"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "licenses": {
                      "description": "License names and their server counts",
                      "items": {
                        "additionalProperties": false,
                        "properties": {
                          "count": {
                            "type": "number"
                          },
                          "name": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "name",
                          "count"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    }
                  },
                  "required": [
                    "categories",
                    "languages",
                    "licenses"
                  ],
                  "type": "object"
                },
                "title": "List directory filter values"
              }
            ],
            "ttlMs": 21600000
          }
        },
        "url": "https://catalog.agentage.io/mcp"
      },
      "latency_ms": 396.57,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "application/json",
          "ratelimit-limit": "60",
          "ratelimit-remaining": "56",
          "ratelimit-reset": "58",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "bad_protocol_payload": {
          "error": {
            "code": -32000,
            "message": "Bad Request: Unsupported protocol version: 1999-99-99 (supported versions: 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05, 2024-10-07)"
          },
          "id": null,
          "jsonrpc": "2.0"
        },
        "bad_protocol_status_code": 400,
        "delete_error": null,
        "delete_status_code": null,
        "expired_session_error": null,
        "expired_session_status_code": null,
        "issues": [
          "missing_session_id",
          "missing_protocol_header"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": false,
        "requested_protocol_version": "2025-03-26",
        "session_id_present": false,
        "transport": "streamable-http"
      },
      "latency_ms": 135.09,
      "status": "warning"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": null
        },
        "initialize_capability_keys": [
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 200,
          "probe_status": "missing"
        }
      },
      "latency_ms": 136.59,
      "status": "missing"
    }
  },
  "failures": {
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "error": "Non-MCP content type: text/html; charset=utf-8",
      "non_mcp_content_type": "text/html; charset=utf-8",
      "url": "https://catalog.agentage.io/.well-known/oauth-protected-resource"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "server_card": {
      "error": "Non-MCP content type: text/html; charset=utf-8",
      "non_mcp_content_type": "text/html; charset=utf-8",
      "url": "https://catalog.agentage.io/.well-known/mcp/server-card.json"
    }
  },
  "remote_url": "https://catalog.agentage.io/mcp",
  "server_card_payload": null,
  "server_identifier": "github-agentage/find-mcp"
}
Capabilities
Use-case taxonomy
development search web
Transport compliance drilldown
Probe status
Warning
Transport
streamable-http
Session header
no
Protocol header
no
Bad protocol response
400
DELETE teardown
n/a
Expired session retry
n/a
Last-Event-ID visible
no

Issues: missing_session_id, missing_protocol_header

Request association
Status
Missing
Advertised capabilities
none
Observed idle methods
none
Violating methods
none
Probe HTTP status
n/a
Issues
none
Connector replay
Status
OK
Backward compatible
✓
Would break after refresh
✕
Added tools
none
Removed tools
none
Additive output changes
none
Required-argument replay breaks
ToolAdded required argsRemoved required args
No required-argument replay breaks detected.
Output-schema replay breaks
ToolRemoved propertiesAdded properties
No output-schema replay breaks detected.