mcpField
R
rendezvous-mcp

rendezvous-mcp

Local
github.com/forgeswornMaps & Travel0Updated 1w ago

About rendezvous-mcp

rendezvous-mcp is an MCP server for finding fair meeting points, aimed at AI applications planning meetups using participant travel times and venue data. It ranks candidate venues by isochrone-based travel-time fairness rather than relying on geographic midpoints.

Key features

  1. 01Score venues by travel-time fairness
  2. 02Search nearby venues
  3. 03Generate isochrones
  4. 04Provide turn-by-turn directions
  5. 05Support multiple participants

Use cases

  1. 01Find a fair lunch meeting point for a group
  2. 02Compare travel times to candidate venues
  3. 03View areas reachable within a time limit
  4. 04Get driving directions to a meeting venue

MCP support

It exposes venue search, fairness scoring, isochrone, and directions tools to MCP clients, and supports stdio and Streamable HTTP transports.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"dev-forgesworn-rendezvous": {
"command": "npx",
"args": [
"-y",
"rendezvous-mcp"
],
"env": {
"VALHALLA_URL": "<VALHALLA_URL>"
}
}
}
}
Run commandnpx -y rendezvous-mcp
Environment variables to set
VALHALLA_URLValhalla routing engine URL

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmrendezvous-mcp1.1.3

Tools

5

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
venuesarrayYesCandidate venues to score (1–50)
fairnessenumNoScoring strategy: min_max (default, minimise longest journey), min_total (minimise total travel), min_variance (equalise travel times)min_max | min_total | min_variance
participantsarrayYesParticipant locations (2–10 people)
transport_modeenumYesHow participants will traveldrive | cycle | walk

Details

From the project README

rendezvous-mcp

Nostr: npub1mgvlrnf5hm9yf0n5mf9nqmvarhvxkc6remu5ec3vf8r0txqkuk7su0e7q2

Fair meeting points for AI — isochrone-based fairness, not naive midpoints.

npm licence TypeScript Nostr GitHub Sponsors

MCP server for AI-driven meeting point discovery. Give your AI the ability to answer "where should we meet?" using real travel times, venue availability, and fairness algorithms.

Works out of the box — free public routing, no API keys needed. Self-host Valhalla for unlimited queries, or use L402 Lightning credits for our hosted endpoint.

Tools

ToolDescription
score-venuesScore candidate venues by travel time fairness for 2–10 participants
search-venuesSearch for venues near a location using OpenStreetMap
get-isochroneGet a reachability polygon (everywhere reachable within N minutes)
get-directionsGet directions between two points with turn-by-turn steps
store-routing-credentialsStore L402 macaroon + preimage after Lightning payment

Quick start

Add to your MCP client config (Claude Code, Claude Desktop, Cursor, etc.):

{
  "mcpServers": {
    "rendezvous": {
      "command": "npx",
      "args": ["rendezvous-mcp"]
    }
  }
}

Then ask your AI: "Where's a fair place for Alice in London, Bob in Bristol, and Carol in Birmingham to meet for lunch?"

Remote (HTTP/SSE)

For ChatGPT, remote AI agents, or any client that connects over HTTP:

TRANSPORT=http npx rendezvous-mcp

Starts a Streamable HTTP server on port 3002 with the MCP endpoint at /mcp.

ChatGPT connector

In ChatGPT settings, add an MCP server with:

  • URL: http://your-host:3002/mcp
  • Transport: Streamable HTTP

Configuration

VariableDefaultDescription
TRANSPORTstdioTransport mode: stdio or http
PORT3002HTTP server port (HTTP mode only)
HOST0.0.0.0HTTP bind address (HTTP mode only)
VALHALLA_URLhttps://routing.trotters.ccRouting engine URL
OVERPASS_URLPublic endpointsVenue search API

Self-hosted routing

For unlimited queries with no rate limits, run your own Valhalla instance:

{
  "mcpServers": {
    "rendezvous": {
      "command": "npx",
      "args": ["rendezvous-mcp"],
      "env": {
        "VALHALLA_URL": "http://localhost:8002"
      }
    }
  }
}

How it works

  1. User asks "Where should we meet?"
  2. AI geocodes participant locations
  3. AI calls search-venues to find candidate venues near the area
  4. AI calls score-venues with participants + candidates — returns ranked results with travel times and fairness scores
  5. AI presents the fairest option with travel times for each person

For deeper analysis, the AI can use get-isochrone to visualise reachability and get-directions for turn-by-turn navigation.

L402 payments

The default routing endpoint (routing.trotters.cc) offers free requests. When the free tier is exhausted, tools return a payment_required response with a Lightning invoice. After payment, call store-routing-credentials to store the macaroon for the session.

Self-hosted Valhalla has no payment requirement.

Architecture

Thin MCP wrapper over rendezvous-kit — the open-source TypeScript library for isochrone intersection, venue search, and fairness scoring. Each tool is an extracted handler function (testable without MCP) plus a registration one-liner.

Development

npm install
npm run build
npm test

Licence

MIT

Support

For issues and feature requests, see GitHub Issues.

If you find rendezvous-mcp useful, consider sending a tip:

  • Lightning: [email protected]
  • Nostr zaps: npub1mgvlrnf5hm9yf0n5mf9nqmvarhvxkc6remu5ec3vf8r0txqkuk7su0e7q2

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.