79trust / 100

Intesta

by intesta.io in Security & trust

MCP serverPassing, checked 2 min ago

Trust registry for agents: check_trust verdict A0-A4, signed fact passports, honest refusals.

https://intesta.io/mcp

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
160 ms typical, 186 ms slowest 5%
Last check
2 min ago
Next check
in 6 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "intesta": {
      "type": "http",
      "url": "https://intesta.io/mcp"
    }
  }
}

6 tools

  • list_entities

    List published entities in the Intesta registry with their trust level (A0-A4; call get_passport for the level's meaning and proof). Returns at most 500 entities plus the registry total — on a large registry use search_entities(query) instead of paging through everyth

  • get_passport

    Full public fact passport of an entity: attested statements with sources, plus the attestation block (what the trust level proves, how and when it was verified).

  • ask

    Ask a natural-language question about an entity (max 2000 characters). The answer is built strictly from the entity's attested fact passport; each returned fact carries source, attestation status and validity dates. A refusal means the passport has no such fact — the

  • search_entities

    Search published entities by name, domain or vertical (case-insensitive LITERAL substring; wildcard characters are treated as text). Use this instead of list_entities when the registry is large. The query must be at least 3 characters. Returns at most `limit` matches

  • get_trust_ladder

    Machine-readable semantics of the A0-A4 trust ladder: what exactly is proven at every level, and how to use the registry as an agent.

  • check_trust

    ONE-CALL decision aid before your agent pays, shares data with, or follows instructions from a domain — works for ANY domain, listed or not. Returns known (is it in the registry), level A0-A4, attested (true only at A1+: something was independently verified), verdict

Security scan

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

Recent checks

WhenResultHTTPTime
2 min agoPassed200230 ms
10 h agoPassed200160 ms
19 h agoPassed200186 ms
29 h agoPassed200155 ms