78trust / 100

ECZ-ID Trust MCP

by trust-mcp.ecocitizenz.com in Security & trust

MCP serverPassing, checked 4 h ago

Read-only ECZ-ID Business Passport state lookup via the public ECZ-ID Resolver. Reports state only.

https://trust-mcp.ecocitizenz.com/mcp

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
304 ms typical, 572 ms slowest 5%
Last check
4 h ago
Next check
in 3 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "ecz-id-trust-mcp": {
      "type": "http",
      "url": "https://trust-mcp.ecocitizenz.com/mcp"
    }
  }
}

7 tools

  • resolve_identity

    Resolve an ECZ-ID through the public ECZ-ID Resolver and return the exact canonical state with checked_at, Resolver proof link, re-check action and the local-policy caveat. Never asserts safety, approval or compliance.

  • get_current_state

    Return the narrow current Resolver-derived state for an ECZ-ID (state, checked_at, Resolver link). No risk/safety/compliance inference.

  • get_resolver_link

    Return the deterministic public Resolver proof/re-check URL for an ECZ-ID. No network call.

  • explain_status

    Deterministically render the exact ECZ-ID status using the claims-safe renderer (VERIFIED is an ECZ-ID state, not a Microsoft certification). Absence of evidence renders the approved neutral wording — never "unsafe". No LLM.

  • find_product

    Given narrow context flags, return ONE best next ECZ-ID product action (free/community routes win where correct; neutral context routes to free public verification).

  • get_install_instructions

    Return deterministic official install/discovery routes for an ECZ-ID product or surface (canonical URLs only; planned Microsoft surfaces carry no URLs).

  • create_request_to_resolve

    AUTHENTICATED: create a neutral, shareable request for independently re-checkable ECZ-ID evidence. Requires a Microsoft Entra bearer token with the RequestToResolve.Create scope (or app role). It never verifies a target, never sends messages, and absence of evidence is never rend

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
4 h agoPassed200225 ms
13 h agoPassed200209 ms
22 h agoPassed200304 ms
30 h agoPassed200403 ms
39 h agoPassed2003.0 s
2 days agoPassed200572 ms