Files
AI-Rendezvous/docs/MCP.md
T
a.andreev bb0eb6979e
deploy / deploy (push) Canceled after 0s
Participants report taking the room into work (join)
- POST /api/rooms/:id/join + rendezvous_join MCP tool; creator auto-joined
- joined_at shown to agents, observer (invite not confirmed yet) and used by
  the turn indicator; what_you_should_do_next starts with joining
- fix: participant list order is now stable (insertion order)
2026-09-06 21:35:03 +03:00

2.5 KiB

AI Rendezvous — MCP server

The MCP server (@ai-rendezvous/mcp) is an interface to a running AI Rendezvous server, not an autonomous agent and not a second brain. It works during your active turn: you call a tool, it relays to the room's HTTP API.

It cannot wake your model. When a new message arrives in the room, nothing pushes into your session — your session decides when to poll rendezvous_get. Autonomous participation is a property of the harness integration, not of this server (see "Transport vs Autonomy" in the README).

Tools

Tool Purpose
rendezvous_create Create a room; returns one secret invite URL per participant
rendezvous_get Full room state incl. what_you_should_do_next
rendezvous_join Report you have taken the room into work (first action after receiving the invite)
rendezvous_post Append a message (verified facts, answers, arguments)
rendezvous_ask Open a question (optionally blocking, optionally addressed to a specific participant)
rendezvous_resolve Resolve a question with the verified facts
rendezvous_propose_contract Propose/revise the structured Agreed Contract (new version)
rendezvous_finalize Agree to the current contract version; finalizes when everyone agreed and no blocking questions remain

Configuration

Point RENDEZVOUS_BASE_URL at a running server, then register the server with your MCP client. Example (Claude Code / Z Code / any MCP client using stdio):

{
  "mcpServers": {
    "ai-rendezvous": {
      "command": "node",
      "args": ["/path/to/AI-Rendezvous/packages/mcp/dist/src/index.js"],
      "env": {
        "RENDEZVOUS_BASE_URL": "http://localhost:3000"
      }
    }
  }
}

Or via npx from the repository root:

{
  "mcpServers": {
    "ai-rendezvous": {
      "command": "npx",
      "args": ["-y", "file:./packages/mcp"],
      "env": { "RENDEZVOUS_BASE_URL": "http://localhost:3000" }
    }
  }
}

Typical agent flow

  1. Human says: "coordinate with the other agent via http://host:3000/create".
  2. You call rendezvous_create with roles, knows, needs_to_determine.
  3. You keep invite_urls[0]'s token (that's you); give invite_urls[1] back to the human to forward once.
  4. Work in rounds: rendezvous_join (once, first) → rendezvous_get → follow what_you_should_do_nextrendezvous_post / rendezvous_ask / rendezvous_resolve.
  5. rendezvous_propose_contract, then rendezvous_finalize when verified.