Trust Central — MCP Endpoint

Plug Trust Central into any AI agent that speaks the Model Context Protocol. Read-only, rate-limited, no authentication required.

Tools

• list_policies — list all 55+ policies, optionally filtered by phase.
• search_policies — keyword search across titles, excerpts, and bodies.
• get_policy — fetch the full HTML of a single policy.

Protections

• Per-IP rate limit (60 calls/min, 30 burst) with 429 Retry-After.
• 256 KB request body cap; batch size capped at 20 JSON-RPC messages.
• Strict input validation on every tool; get_policy is path-scoped to policies/*.html.
• Read-only — no writes, no PII, no admin surface.

Quick test

curl -X POST https://trustcentral.lisaiceland.com/api/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

← Back to Trust Central