io.github.agenttrust-ai/agenttrust

up checked 2026-11-11T06:38:16.204Z

Unclaimed · Unverified

Publisher-provided title

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

Publisher-provided description

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

Summary by lookupd

Checks an AI agent or MCP endpoint's stored trust observations before calling it; read-only, no API key, returns an allow or avoid decision.

Install

Claude Code, remote (streamable-http)

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

Claude Code, remote (streamable-http)

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

Codex, remote (streamable-http)

codex mcp add agenttrust --url https://getagenttrust.com/api/mcp/public

Codex, remote (streamable-http)

codex mcp add agenttrust --url https://getagenttrust.com/api/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

check_agent_trust Pre-invocation trust check for an unknown AI agent or MCP server endpoint. Pass the exact URL you are about to call as endpointUrl to get what AgentTrust has ob
assess_agent Use-or-avoid decision about an AI agent or MCP server endpoint, built from AgentTrust's stored observations of its exact URL. Returns decision (allow_with_cauti

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.agenttrust-ai/agenttrust.svg)](https://lookupd.com/servers/io.github.agenttrust-ai/agenttrust)