rendezvous-mcp CLAUDE.md

rendezvous-mcp CLAUDE.md is an instructions file for coding agents from forgesworn/rendezvous-mcp. It costs 538 tokens per session, scanned A, original, MIT.

A set of project-specific instructions for the rendezvous-mcp codebase, covering its conventions, file layout, build and test commands, and handler-extraction pattern. rendezvous-mcp is an MCP server for finding fair meeting points.

In plain words
What is it for?
Use it when working on this repository's TypeScript MCP server, routing, venue-search, directions, isochrone, or credential-storage code.
Why use it?
It gives an agent the local rules needed to make compatible changes and run the project correctly.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/forgesworn/rendezvous-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/forgesworn/rendezvous-mcp

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rendezvous-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/forgesworn/rendezvous-mcp/claude-md.svg)](https://agentmods.dev/instructions/forgesworn/rendezvous-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/forgesworn/rendezvous-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/forgesworn/rendezvous-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 538 This file is loaded in full into every session.
When invoked 538 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00538 $0.00538
Opus 5 $0.00269 $0.00269
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 5d ago against content hash 89e5f0cea69d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rendezvous-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — rendezvous-mcp

MCP server for AI-driven fair meeting point discovery. Thin wrapper over rendezvous-kit exposing 5 tools via the Model Context Protocol.

Conventions

  • British English everywhere — favour, colour, behaviour, licence, initialise, metre
  • Never use console.log() — stdio transport reserves stdout for JSON-RPC. Use console.error() for all debug output.
  • Git: commit messages use type: description format. Do NOT include Co-Authored-By lines.
  • ESM-only with .js extensions in imports
  • TypeScript strict mode — no any, no implicit returns

Project structure

src/
  index.ts                — server entry point, dual transport (stdio/HTTP)
  routing.ts              — RoutingClient wrapping ValhallaEngine with L402 handling
  l402.ts                 — L402State credential storage + types
  tools/
    score-venues.ts       — score candidate venues by travel time fairness
    search-venues.ts      — search Overpass for venues near a location
    isochrone.ts          — compute reachability polygon
    directions.ts         — turn-by-turn routing
    store-credentials.ts  — store L402 macaroon + preimage after payment

Build & test

npm run build      # tsc → build/
npm test           # vitest run
npm run typecheck  # tsc --noEmit
npm start          # stdio mode (default)
npm run start:http # HTTP mode on port 3002

Handler extraction pattern

Each tool file exports two things:

  1. handle*() — extracted handler function (testable without MCP framework)
  2. register*Tool() — one-liner that registers the handler with the MCP server

This pattern keeps tool logic testable and registration minimal.

Environment variables

Variable Default Description
TRANSPORT stdio Transport mode: stdio or http
PORT 3002 HTTP server port (HTTP mode only)
HOST 0.0.0.0 HTTP bind address (HTTP mode only)
VALHALLA_URL https://routing.trotters.cc Routing engine URL
OVERPASS_URL Public endpoints Venue search API

Read the full file on GitHub · 55 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 55 lines · 538 tokens per session scan A 89e5f0cea69d

Subscribe to this mod's changes

rendezvous-mcp CLAUDE.md is an instructions file published in the GitHub repository forgesworn/rendezvous-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 538 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.