Claude MarketplacesSubmit
sentinelsignal avatar

MCP Verify

io.sentinelsignal/verify

If you're building agents that call third-party MCP servers, this is a policy and trust layer that sits between your agent and the rest of the ecosystem. It exposes search_servers to discover tools, decide_agent_call to enforce allow/deny rules at runtime, create_mandate for signed governance policies, and get_evidence_pack for audit trails. The backend continuously scores over 21,000 public MCP servers on freshness, auth posture, write risk, and payment signals, then serves that intel via a read-only MCP interface at verify.sentinelsignal.io/mcp. Reach for it when you need centralized visibility into which tools your agents are invoking, compliance-ready logs, or a way to block risky servers before they execute.

tools
4
transport
HTTP
last updated
May 24, 2026
Open website

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

search_serversSearch and rank MCP servers by capability, auth preference, client target, and risk tolerance.6 params

Search and rank MCP servers by capability, auth preference, client target, and risk tolerance.

Parameters* required
auth_preferencestring
Preferred auth mode. Use unauthenticated when the agent must avoid login flows.one of any · oauth · unauthenticated
capabilitiesarray
Normalized capability taxonomy terms such as healthcare, search, read, exec, files, oauth, or prompts.
client_targetstring
Optional target client or integration surface.one of openai_connectors · claude_desktop · smithery · generic_http · healthcare
limitinteger
Maximum number of ranked candidates to return.
querystring
Optional free-text query to bias ranking toward a specific use case or domain.
risk_tolerancestring
How much tool-surface risk is acceptable.one of any · low · medium · high
recommend_serversRecommend MCP servers for a plain-language task and return ranked matches with install config.6 params

Recommend MCP servers for a plain-language task and return ranked matches with install config.

Parameters* required
auth_preferencestring
Preferred auth mode.one of any · oauth · unauthenticated
capabilitiesarray
Optional explicit capability constraints that override or extend the inferred task capabilities.
client_targetstring
Optional target client or integration surface.one of openai_connectors · claude_desktop · smithery · generic_http · healthcare
limitinteger
Maximum number of recommendations to return.
risk_tolerancestring
How much tool-surface risk is acceptable.one of any · low · medium · high
taskstring
Plain-language task description such as 'I need an MCP for healthcare denial scoring in OpenAI connectors'.
get_server_reportReturn the full machine-readable verify report for a specific MCP server identifier.1 params

Return the full machine-readable verify report for a specific MCP server identifier.

Parameters* required
identifierstring
Canonical server identifier in namespace/name format.
compare_serversCompare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.1 params

Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.

Parameters* required
identifiersarray
Canonical server identifiers in namespace/name format.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Website
verify.sentinelsignal.io
Transport
HTTP
Registry
MCP registry, active

More from sentinelsignal