SBB Open Data MCP Server
An MCP server for Swiss Federal Railways (SBB) open data, enabling AI models to query real-time disruptions, passenger frequencies, station details, and more without an API key.
README
SBB Open Data MCP Server
🇩🇪 Deutsch | 🇬🇧 English
An Model Context Protocol (MCP) server for Swiss Federal Railways (SBB) open data via data.sbb.ch. No API key required.
What is this?
This server connects AI models (Claude, GPT-4, Llama, etc.) directly to public SBB data — no copy-pasting or manual API calls required. A question like "How many passengers passed through Zürich HB every day in 2024?" is answered with real measured data.
The server is model-agnostic and works with any MCP-compatible client.
Available Tools (10)
| Tool | Description | Data Update |
|---|---|---|
sbb_get_passenger_frequency |
Boardings/alightings by station and year (daily avg.) | Annual |
sbb_get_rail_disruptions |
Live rail traffic messages | Every 5 min. |
sbb_get_infrastructure_construction_projects |
Infrastructure construction (stations, lines) | Ongoing |
sbb_get_real_estate_projects |
SBB real estate development projects | Daily |
sbb_get_trains_per_segment |
Train counts per route segment (SBB, BLS, SOB …) | Annual |
sbb_get_platform_data |
Platform data (length, type, area) | Ongoing |
sbb_get_rolling_stock |
Rolling stock (capacity, year built) | Ongoing |
sbb_compare_stations |
Compare up to 10 stations (multi-dataset) | – |
sbb_search_stations |
Search stops (Swiss DiDok register, all CH) | Ongoing |
sbb_list_datasets |
List all ~89 SBB open datasets | – |
All tools support response_format: "markdown" (human-readable) and "json" (machine-readable), plus pagination.
Installation
Prerequisites
Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
Claude Desktop (stdio)
Open the config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"sbb-opendata": {
"command": "uvx",
"args": ["sbb-opendata-mcp"]
}
}
}
Restart Claude Desktop. The server is downloaded automatically on first use.
Other MCP Clients
Works with Cursor, Windsurf, VS Code + Continue, LibreChat, Cline and self-hosted models via mcp-proxy — same configuration as above.
Cloud Deployment (Streamable HTTP)
For remote servers (e.g. Render.com):
git clone https://github.com/malkreide/sbb-opendata-mcp
cd sbb-opendata-mcp
pip install -e .
python -m sbb_opendata_mcp.server --http --port 8000
Local Development
git clone https://github.com/malkreide/sbb-opendata-mcp
cd sbb-opendata-mcp
pip install -e ".[dev]"
# Unit tests (no network required)
PYTHONPATH=src pytest tests/ -v -m "not live"
# Live API smoke tests
PYTHONPATH=src pytest tests/ -v -m live
Example Queries
"How many people boarded at Zürich HB daily in 2024?"
→ sbb_get_passenger_frequency(station_name="Zürich HB", year="2024")
"Are there any current disruptions on the Swiss rail network?"
→ sbb_get_rail_disruptions(limit=10)
"Compare Zürich HB, Bern and Basel SBB by passenger frequency and platform capacity."
→ sbb_compare_stations(stations=["Zürich HB", "Bern", "Basel SBB"], year="2024")
"Which SBB construction projects are active in Zürich?"
→ sbb_get_infrastructure_construction_projects(city="Zürich")
"How many trains run daily on the Zürich–Winterthur route?"
→ sbb_get_trains_per_segment(line_name="Zürich", operator="SBB", year="2025")
"Which stops exist in Wädenswil?"
→ sbb_search_stations(query="Wädenswil", canton="ZH")
Data & License
All data is sourced from the SBB Open Data Portal (OpenDataSoft REST API v2.1).
Data license: NonCommercialAllowed-CommercialAllowed-ReferenceRequired
This server is released under the MIT License and is part of the open source MCP portfolio at github.com/malkreide.
Relationship to Other MCP Servers
| Server | How SBB Open Data Complements It |
|---|---|
| swiss-transport-mcp | Historical depth: passenger context for real-time timetable queries |
| swiss-road-mobility-mcp | Multimodal view: rail hub + micromobility/EV charging |
| zurich-opendata-mcp | Cross-reference: Zurich stops combined with city population and school data |
Technical Details
- Framework: FastMCP + httpx + Pydantic v2
- Transport: stdio (local) and Streamable HTTP (cloud)
- Python: 3.11, 3.12, 3.13
- Tests: 34 unit tests + 5 live API smoke tests
- API: OpenDataSoft REST v2.1 — no authentication needed
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.