Île-de-France Mobilités MCP Server
Provides real-time access to Paris public transport data (métro, RER, bus, tram, Transilien) including live departure times and traffic disruptions through the IDFM PRIM API.
README
Île-de-France Mobilités MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to real-time Paris public transport data through the IDFM PRIM API.
🚇 Overview
This Docker-based MCP server enables AI assistants like Claude to access live information about the Paris public transport network (métro, RER, bus, tram, Transilien trains) managed by Île-de-France Mobilités.
Key Features
- Real-time Departures: Get next departure times for any transport stop
- Traffic Disruptions: Monitor service alerts and disruptions across the network
- Docker Integration: Runs as a containerized MCP server with Docker Desktop
- Secure API Management: Uses Docker MCP Toolkit's secret management
- SIRI Protocol Support: Compatible with the official IDFM PRIM API
🛠️ Technologies
- Python 3.11 with FastMCP framework
- Docker containerization with multi-stage builds
- SIRI (Service Interface for Real Time Information) protocol
- HTTPX for async HTTP requests
- Model Context Protocol for AI assistant integration
📋 Available Tools
| Tool | Status | Description |
|---|---|---|
get_next_departures |
✅ Working | Real-time departure times for specific stops |
get_traffic_info |
✅ Working | Service disruptions and network messages |
search_stops |
❌ Limited API | Stop search (API limitations explained) |
search_routes |
❌ Limited API | Journey planning (API limitations explained) |
get_line_info |
❌ Limited API | Line information (API limitations explained) |
🚀 Quick Start
Prerequisites
- Docker Desktop with MCP Toolkit enabled
- IDFM PRIM API key from prim.iledefrance-mobilites.fr
Installation
-
Clone the repository
git clone <your-repo-url> cd idfm-mcp-server -
Set up your API key
docker mcp secret set IDFM_API_KEY=your-api-key-here -
Build the Docker image
docker build -t idfm-mcp-server . -
Test the server
echo '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}},"id":1}' | \ docker run --rm -i -l x-secret:IDFM_API_KEY=/tmp/api_key.txt -e IDFM_API_KEY_FILE=/tmp/api_key.txt idfm-mcp-server
💡 Usage Examples
With Claude Desktop
Ask natural language questions like:
- "What are the next trains at Châtelet station?"
- "Are there any disruptions on the RER A line?"
- "Show me departure times for stop STIF:StopPoint:Q:41304:"
Direct API Calls
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "get_next_departures",
"arguments": {
"stop_id": "STIF:StopPoint:Q:41304:",
"max_results": "5"
}
},
"id": 1
}
🔧 Configuration
Docker MCP Secrets
The server reads the API key from Docker MCP secrets:
# Set the secret
docker mcp secret set IDFM_API_KEY=your-key-here
# Run with secret mounting
docker run -l x-secret:IDFM_API_KEY=/tmp/api_key.txt -e IDFM_API_KEY_FILE=/tmp/api_key.txt idfm-mcp-server
Environment Variables
| Variable | Description | Default |
|---|---|---|
IDFM_API_KEY |
Direct API key (fallback) | Empty |
IDFM_API_KEY_FILE |
Path to API key file | Empty |
🏗️ Architecture
Claude Desktop → MCP Protocol → Docker Container → IDFM PRIM API
↓
Docker MCP Secrets
The server implements the MCP protocol to provide a secure, standardized interface between AI assistants and the IDFM transport data.
📊 API Limitations
The IDFM PRIM API has evolved and currently supports:
- ✅ SIRI Protocol: Real-time monitoring and disruption data
- ❌ NavItia Protocol: Historical search endpoints have been deprecated
This server provides honest error messages explaining these limitations and suggests alternatives for unavailable functionality.
🔒 Security
- API keys stored securely in Docker MCP secrets
- Non-root user execution in container
- No API key logging or exposure
- Rate limiting awareness (1M requests/day for monitoring)
🐛 Troubleshooting
Common Issues
Tools not appearing in Claude:
- Verify Docker image built successfully:
docker images | grep idfm - Check MCP server registration
- Restart Claude Desktop
Authentication errors:
- Verify secret:
docker mcp secret ls - Ensure API key is valid at PRIM portal
- Check container has secret access
No departure data:
- Verify stop ID format (use SIRI format:
STIF:StopPoint:Q:XXXXX:) - Some stops may not have real-time data
- Check service schedules (reduced on weekends/holidays)
Stop ID Formats
The API requires specific SIRI-compliant stop IDs:
- ✅
STIF:StopPoint:Q:41304:(Châtelet-Les Halles) - ❌
stop_area:IDFM:71571(Old NavItia format)
📈 Rate Limits
- Stop Monitoring: 1,000,000 requests/day
- General Access: 20,000 requests/day
🤝 Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Test with real API data
- Submit a pull request
📄 License
MIT License - see LICENSE file for details
🔗 Resources
- IDFM PRIM API Portal
- Model Context Protocol Specification
- Docker MCP Toolkit Documentation
- Île-de-France Mobilités
📞 Support
For API-related issues, contact IDFM support. For server issues, please open a GitHub issue.
Built with ❤️ for the Paris public transport community
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Neon Database
MCP server for interacting with Neon Management API and databases