AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

io.github.agenttrust-ai/agenttrustVersion 1.0.4

Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

Status

Responds307 msNov 14, 2026, 14:45 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:45 UTC
Latency: 307 ms
Remotes responding: 2 of 2
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://getagenttrust.com/api/mcpResponds307 msNov 14, 2026, 14:44 UTC

No sign-in

Claude Code

claude mcp add --transport http agenttrust https://getagenttrust.com/api/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: agenttrust
Remote MCP server URL: https://getagenttrust.com/api/mcp

Cursor

{
  "mcpServers": {
    "agenttrust": {
      "url": "https://getagenttrust.com/api/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"agenttrust","type":"http","url":"https://getagenttrust.com/api/mcp"}'

Streamable HTTP

https://getagenttrust.com/api/mcp/publicResponds378 msNov 14, 2026, 14:45 UTC

No sign-in

Claude Code

claude mcp add --transport http agenttrust https://getagenttrust.com/api/mcp/public

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: agenttrust
Remote MCP server URL: https://getagenttrust.com/api/mcp/public

Cursor

{
  "mcpServers": {
    "agenttrust": {
      "url": "https://getagenttrust.com/api/mcp/public"
    }
  }
}

VS Code

code --add-mcp '{"name":"agenttrust","type":"http","url":"https://getagenttrust.com/api/mcp/public"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

6 tools

Tools of AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks
	Description		Read-only	Idempotent	Open world
`assess_agent`Immediate use-or-avoid decision about an AI agent or MCP server endpoint, for an agent deciding whether to call it. Returns decision (allow_with_caution, avoid, or insufficient_evidence), confidence, reasonCodes, reachability (the latest stored observation, with its age), initialRisk, the historical reliability score and trustDecision (unchanged), limitations, and freshness. Built only from AgentTrust's stored observations: it never contacts endpointUrl. Reachability is not safety: allow_with_caution never means the agent's behavior is safe. Requires no API key.	Immediate use-or-avoid decision about an AI agent or MCP server endpoint, for an agent deciding whether to call it. Returns decision (allow_with_caution, avoid, or insufficient_evidence), confidence, reasonCodes, reachability (the latest stored observation, with its age), initialRisk, the historical reliability score and trustDecision (unchanged), limitations, and freshness. Built only from AgentTrust's stored observations: it never contacts endpointUrl. Reachability is not safety: allow_with_caution never means the agent's behavior is safe. Requires no API key.	No	Yes	Yes	No
`check_agent_trust`Pre-invocation trust check for an unknown AI agent or MCP server endpoint. Read-only, requires no AgentTrust API key or account. Looks up an agent by its exact invocation URL among AgentTrust's already-observed public agents and returns its status, endpoint-ownership verification, agent reliability score (when available), and a machine-readable trustDecision (recommended, confidence, reasons). Does NOT contact endpointUrl itself during this check — it only reads AgentTrust's own existing monitoring history. An unregistered URL returns { matched: false }, never an error.	Pre-invocation trust check for an unknown AI agent or MCP server endpoint. Read-only, requires no AgentTrust API key or account. Looks up an agent by its exact invocation URL among AgentTrust's already-observed public agents and returns its status, endpoint-ownership verification, agent reliability score (when available), and a machine-readable trustDecision (recommended, confidence, reasons). Does NOT contact endpointUrl itself during this check — it only reads AgentTrust's own existing monitoring history. An unregistered URL returns { matched: false }, never an error.	No	Yes	Yes	No
`get_agent`Get one AgentTrust agent's public profile by slug, including its structured Agent Card, current reliability score, and a machine-readable trustDecision (recommended, confidence, reasons) for deciding whether to invoke it.	Get one AgentTrust agent's public profile by slug, including its structured Agent Card, current reliability score, and a machine-readable trustDecision (recommended, confidence, reasons) for deciding whether to invoke it.	No	Yes	Yes	No
`get_agent_health`Get one agent's current effective health status and monitoring detail — derived from heartbeat freshness for push-mode agents, or the latest pull check otherwise.	Get one agent's current effective health status and monitoring detail — derived from heartbeat freshness for push-mode agents, or the latest pull check otherwise.	No	Yes	Yes	No
`list_agents`Discover AgentTrust agents. Pass `endpointUrl` to check the trust status of a specific external agent by its exact invocation URL before deciding whether to invoke it — the response includes a reliability score, endpoint-ownership verification status, and a machine-readable trustDecision (recommended, confidence, reasons). Without `endpointUrl`, returns the plain paginated listing of public agents, newest first. Requires an API key; for an anonymous pre-invocation check use check_agent_trust.	Discover AgentTrust agents. Pass `endpointUrl` to check the trust status of a specific external agent by its exact invocation URL before deciding whether to invoke it — the response includes a reliability score, endpoint-ownership verification status, and a machine-readable trustDecision (recommended, confidence, reasons). Without `endpointUrl`, returns the plain paginated listing of public agents, newest first. Requires an API key; for an anonymous pre-invocation check use check_agent_trust.	No	Yes	Yes	No
`send_heartbeat`Record a push-style heartbeat for an agent you own, marking it alive right now. The server sets the timestamp; no client-supplied time is accepted.	Record a push-style heartbeat for an agent you own, marking it alive right now. The server sets the timestamp; no client-supplied time is accepted.	No	No	No	No

Details

Registry status: Active
Published: Oct 2, 2026
Updated: Oct 2, 2026
Website: https://getagenttrust.com/docs⁠ (opens in a new tab)
Repository: https://github.com/agenttrust-ai/agenttrust⁠ (opens in a new tab)
Categories: Uncategorized
GDPR: Not declared

Are you the operator? Claim this listing