AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks MCP Server

io.github.agenttrust-ai/agenttrust

What is the AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks MCP server?

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

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

Environment / auth

Authorization
secret
Bearer <API_KEY>. Required to call a tool (list_agents, get_agent, get_agent_health, send_heartbeat); tools/list and initialize work without one. Get a key by creating an account at https://getagenttrust.com/signup.

~/.cursor/mcp.json

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

Active

Whether an AI agent may fetch a URL, on what terms, and at what price. Free, no key, no signup.

MIT

Active

Synthetic checks, nightly regression replay and model-drift alerts for AI agents

MIT

Active

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

TypeScript

MIT

Active

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

MIT

Active

Real estate deal memo from a US address: AVM, rent, comps, cap rate, cash-on-cash, DSCR, red flags.

MIT

Active

Whether a registry MCP server works for a stock client, and what changed in its tools. Free, no key.

MIT