What API key is required?
You need an SNCF API key obtained from the Navitta service on the SNCF API Portal. The key is a UUID string.
SNCF API MCP Server
@Kryzo
基本情報
SNCF API MCP Server について
This project provides a modular Python wrapper for the SNCF API, with an MCP server interface that integrates seamlessly with Claude Desktop for intelligent journey planning and train information retrieval across France.
SNCF API MCP Server の設定
SNCF API MCP Server のツール
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is SNCF API MCP Server?
A modular Python wrapper for the SNCF API that provides an MCP server interface for Claude Desktop, enabling intelligent journey planning and train information retrieval across France.
How to use SNCF API MCP Server?
Clone the repository, install dependencies (pip install -r requirements.txt), obtain an SNCF API key from the Navitia service on the SNCF portal, then configure Claude Desktop by adding the server to its claude_desktop_config.json with the path to sncf_server.py and the API key. Once configured, Claude can invoke MCP tools via natural language prompts.
Key features of SNCF API MCP Server
- Intelligent journey planning between French cities
- Comprehensive station details (transport types, nearby places, coordinates)
- Real-time departure and arrival schedules
- Disruption monitoring across the SNCF network
- Smart station lookup by city, name, or coordinates
- Fallback hardcoded coordinates for major cities
Use cases of SNCF API MCP Server
- Plan a train journey from Paris to Lyon and get departure/arrival times
- Check available transport types at a specific station (e.g., Gare de Lyon)
- View the next five departures from a station in real time
- Monitor current disruptions affecting a route (e.g., Paris to Marseille)
- Find nearby points of interest around a train station
よくある質問
What are the runtime dependencies?
Python 3.6+ and the packages `requests`, `pandas`, and `mcp`. Also requires the `train_stations_europe.csv` file in the correct location.
Where does station location data come from?
The server uses a CSV database (`train_stations_europe.csv`) and hardcoded coordinates for major French cities as a fallback when the API search fails.
What should I do if I get "No stations found for city"?
Try a more specific city name. For smaller cities, use the name of a nearby larger city. The system’s hardcoded coordinates for major French cities should work reliably.
How do I fix a "Failed to connect to SNCF API" error?
Check your internet connection, verify the API key is valid and not expired, and try again later as the SNCF API may be experiencing downtime.
「開発者ツール」の他のコンテンツ
DrUrls
DrUrlsDrUrls audits websites for SEO, and its MCP server lets Claude, ChatGPT, Claude Code, Cursor or VS Code work with those audits directly: list your sites with their latest score and grade, read each issue across SEO, perf
LocalCan
LocalCanGives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
82
LastPing
LastPingKnow when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Rams
HSLA0001 Inc.Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url
screenshotrun-mcp
screenshotrunGive your AI agent the ability to see any webpage. Capture screenshots from Claude, Cursor, or any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, custom viewport, ad bloc
コメント