Categories › Security › Code & dependency scanning
Trust registry for agents: check_trust verdict A0-A4, signed fact passports, honest refusals.
Remote server: your requests and data go to intesta.io. Claude Code: claude mcp add --transport http intesta https://intesta.io/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
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). Returnsget_passport — Full public fact passport of an entity: attested statements with sources, plus the attestation block (what the trust level proves, how and wask — Ask a natural-language question about an entity (max 2000 characters). Retrieval is constrained to the entity's passport; each returned factsearch_entities — Search published entities by name, domain or vertical (case-insensitive LITERAL substring; wildcard characters are treated as text). Use thiget_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.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.