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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。