mcpField
S
swisstrip-mcp

swisstrip-mcp

Remote
github.com/FabsbagsMaps & Travel0Updated 26w ago
Repository

About swisstrip-mcp

swisstrip-mcp connects AI assistants to Swiss Federal Railways (SBB/CFF/FFS) schedules, fares, and ticket links for people planning rail travel in Switzerland. It uses SwissTrip's hosted MCP service and is an independent third-party implementation, not an official SBB MCP.

Key features

  1. 01Search stations, addresses, and points of interest
  2. 02Find train times between stations
  3. 03View trips and intermediate stops
  4. 04Find earlier or later connections
  5. 05Check discounted ticket prices
  6. 06Get SBB.ch ticket links

Use cases

  1. 01Find Swiss stations and nearby places
  2. 02Plan rail journeys between two stations
  3. 03Compare fares with available discounts
  4. 04Open SBB.ch to purchase a ticket

MCP support

The client connects to SwissTrip's hosted MCP service, at https://mcp.swisstrip.app/mcp by default. It can be configured with stdio MCP clients and supports custom connectors pointed at that endpoint.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.swisstrip.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npmswisstrip-mcp0.6.3

Tools

Details

From the project README

swisstrip-mcp

The canonical SwissTrip MCP client. Connects AI assistants to Swiss Federal Railways (SBB / CFF / FFS) data: train schedules, station search, ticket prices, and direct ticket purchase links.

Backed by SwissTrip's hosted MCP service at https://mcp.swisstrip.app/mcp. Independent third-party implementation; not the official SBB MCP.

Install

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "swisstrip": {
      "command": "npx",
      "args": ["-y", "swisstrip-mcp"]
    }
  }
}
Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "swisstrip": {
      "command": "npx",
      "args": ["-y", "swisstrip-mcp"]
    }
  }
}
Gemini CLI / Continue / other stdio MCP clients

Same pattern: command: npx, args: ["-y", "swisstrip-mcp"].

ChatGPT (Plus / Pro / Business / Enterprise with Developer Mode)

No install required. Add a custom connector pointing at:

https://mcp.swisstrip.app/mcp

Tools

  • search_stations — find Swiss stations, addresses, and points of interest
  • search_connections — train schedules between two stations
  • get_trip_details — detailed trip with all intermediate stops
  • get_more_connections — earlier or later trains for a previous search
  • get_prices — ticket prices with Halbtax / GA / Sparbillet discounts
  • get_ticket_link — direct purchase link to SBB.ch

Languages

Tool descriptions and natural-language responses available in 9 languages: English, German, French, Italian, Spanish, Portuguese, Dutch, Polish, Russian.

Optional configuration

Environment variablePurpose
SWISSTRIP_MCP_URLOverride the hosted server URL. Default: https://mcp.swisstrip.app/mcp.
SBB_MCP_URLSame as above (legacy name, still supported).

Aliases (also published, all spawn this canonical package)

The following npm packages are brand-protective aliases that spawn swisstrip-mcp:

  • swisstrip, swisstrip-ai, swisstrip-server — SwissTrip-branded
  • sbb-mcp, sbb-mcp-official, sbb-cff-ffs-mcp — SBB-themed (may transfer to SBB AG on request)
  • swiss-rail-mcp, swiss-railways-mcp, swiss-train-mcp — generic descriptive

Recommended: install swisstrip-mcp directly. The aliases exist for discoverability and brand protection.

License

Proprietary. See LICENSE. © 2026 SwissTrip.

For commercial licensing inquiries: [email protected].

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.