idfm-mcp-server: Instructions file for Claude Code

CLAUDE.md

idfm-mcp-server CLAUDE.md is an instructions file for Claude Code from HeshamWM/idfm-mcp-server. It costs 1,348 tokens per session, scanned A, original, MIT.

A set of coding instructions for an MCP server that connects Claude Desktop to Paris public transport data. It describes the APIs, authentication, available tools, and data formats.

In plain words
What is it for?
Use it when implementing or maintaining tools that search Île-de-France stops, show upcoming departures, plan journeys, or report service disruptions.
Why use it?
It gives the coding agent project-specific details needed to work with the transport service correctly, including real-time data and secure API access.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is HeshamWM/idfm-mcp-server's own configuration. It tells Claude Code how to work on idfm-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything idfm-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HeshamWM/idfm-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HeshamWM/idfm-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/HeshamWM/idfm-mcp-server

Made for: Claude Code.

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 idfm-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/heshamwm/idfm-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/heshamwm/idfm-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/heshamwm/idfm-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/heshamwm/idfm-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for idfm-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/heshamwm/idfm-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/heshamwm/idfm-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,348 This file is loaded in full into every session.
When invoked 1,348 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01348 $0.01348
Opus 5.5 $0.00539 $0.00539
Sonnet 5.5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 2mo ago against content hash c9348578fd2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

idfm-mcp-server CLAUDE.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -H "apiKey: YOUR_KEY" \
CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Île-de-France Mobilités MCP Server Implementation Guide

Overview

This MCP server provides Claude Desktop with access to the Paris public transport network (Île-de-France Mobilités) through the PRIM API.

Implementation Details

API Integration

The server integrates with the PRIM (Platform for Regional Information on Mobility) API which provides:

  1. SIRI Lite API - Real-time departures (/stop-monitoring)
  2. Navitia API - Journey planning and search (/v2/navitia/)
  3. General Messages API - Traffic disruptions (/general-message)

Authentication

Tools Implemented

1. get_next_departures
  • Purpose: Get real-time departure times for a specific stop
  • Input: Stop ID (from search_stops), optional max results
  • Output: List of next departures with line, destination, and time
  • API: SIRI Lite Stop Monitoring endpoint
2. search_stops
  • Purpose: Find stop IDs by searching for station names
  • Input: Search query (station name or location)
  • Output: List of matching stops with IDs and coordinates
  • API: Navitia Places endpoint
  • Note: Essential for finding stop IDs needed by get_next_departures
3. search_routes
  • Purpose: Calculate journey itineraries between two locations
  • Input: From location, to location, optional datetime
  • Output: Multiple journey options with transfers and timings
  • API: Navitia Journeys endpoint
  • Formats: Can use coordinates (lat;lon) or place IDs
4. get_traffic_info
  • Purpose: Get real-time service disruptions and messages
  • Input: Optional line ID to filter
  • Output: List of current disruptions and service messages
  • API: SIRI Lite General Message endpoint
5. get_line_info
  • Purpose: Get detailed information about a transport line
  • Input: Line ID
  • Output: Line details, routes, and directions
  • API: Navitia Lines endpoint

Read the full file on GitHub · 183 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. 2mo ago First seen · 183 lines · 1,348 tokens per session scan A c9348578fd2d

Subscribe to this mod's changes

idfm-mcp-server CLAUDE.md is an instructions file published in the GitHub repository HeshamWM/idfm-mcp-server (2 stars, last pushed 11mo ago), licensed MIT. It adds 1,348 tokens to every session, about $0.0054 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

idfm-mcp-server CLAUDE.md compared with instructions from other repositories

idfm-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
idfm-mcp-server CLAUDE.mdHeshamWM/idfm-mcp-serverInstructions file211mo agoMITA1,348Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode