Advertise
MCP.so
Sign In

Caltrain MCP Server

@davidyen1124

Repository

Basic information

Category

Productivity

License

NOASSERTION

Transports

stdio

Author

davidyen1124

Submitted by

David

About Caltrain MCP Server

A Model Context Protocol (MCP) server for Caltrain schedules. Get real-time train departures using GTFS data, designed for Claude Desktop and other MCP clients.

#caltrain#mcp#train-schedules

Caltrain MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "caltrain": {
      "command": "uvx",
      "args": [
        "caltrain-mcp"
      ]
    }
  }
}

Caltrain MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is caltrain-mcp?

caltrain-mcp is a Model Context Protocol server that provides Caltrain schedule information using official GTFS data. It is intended for users of MCP-compatible clients (like Claude Desktop) who need to look up train departures, stations, and travel times between any two Caltrain stops.

How to use caltrain-mcp?

Configure caltrain-mcp in your MCP client (e.g., Claude Desktop) by adding "caltrain": { "command": "uvx", "args": ["caltrain-mcp"] } to the MCP configuration file. The server can also be tested directly via Python imports or started with uvx caltrain-mcp. It relies on local GTFS data that must be fetched first by running fetch_gtfs.py.

Key features of caltrain-mcp

  • Real‑time (GTFS‑based) train schedules between any two stations
  • Look up all 31 Caltrain stations by full name, short name, or abbreviation
  • Query departures at a specific time using the when_iso parameter
  • Smart partial matching of station names (e.g., "diridon" matches "San Jose Diridon")
  • Supports weekday/weekend service calendars from official GTFS data

Use cases of caltrain-mcp

  • Ask your AI assistant for the next trains from San Jose Diridon to San Francisco
  • Find all available Caltrain stations without memorizing names
  • Plan a commute at a precise time and date, using GTFS data
  • Get departure times for the Gilroy extension line

Frequently asked questions

1

What GTFS data does caltrain-mcp use?

It uses official Caltrain GTFS data, including `stops.txt`, `trips.txt`, `stop_times.txt`, and `calendar.txt`, which are downloaded by running `fetch_gtfs.py`.

2

How do I install and run caltrain-mcp?

Install the `uv` package manager, run `uv sync` to install dependencies, then download the GTFS data with `uv run python scripts/fetch_gtfs.py`. Finally, configure your MCP client to run `uvx caltrain-mcp`.

3

What tools does caltrain-mcp expose?

It exposes two tools: `next_trains(origin, destination, when_iso=None)` to get upcoming departures, and `list_stations()` to list all 31 Caltrain stations.

4

How does caltrain-mcp communicate?

The server communicates via stdin/stdout using the Model Context Protocol (MCP). It does nothing when run directly in a terminal.

5

Are there any known limitations?

The README notes that actual arrival times may vary and that the server relies on the official GTFS data, so accuracy depends on that data. It handles mixed integer/string GTFS fields and supports 24+ hour time format.

Comments

More Productivity MCP servers

Taklo

Official MCP server for Taklo, all-in-one software for installation and maintenance companies in the Netherlands and Belgium (CRM, work orders, quotes, invoicing, VAT). Gives AI assistants live answers about Taklo's pric

AgentGrid.io (by Anima)

Anima

Shared workspace for humans and AI agents by Anima. Create, version, publish, and share live apps, docs, and files from any agent, with per-agent access control. Support all types of agents: Grok Bot, Muse AI, OpenAI Dot

AgileHero

All-in-one agile project management built for AI agents and people. Over MCP your agent works across every module: board, backlog, roadmap, whiteboards, retros, metrics and wiki.

Mailercloud

Mailercloud

Connect AI assistants to Mailercloud, the email marketing platform — manage campaigns, contacts, lists, templates, and sending, plus AI-powered campaign analysis and deliverability audits. Endpoint: https://mcp.mailerclo

fynk

fynk

Draft, find, negotiate, analyze and sign contracts in fynk. Create documents via AI, from templates or PDFs, manage parties, signatories and fields, and send for e-signature, all with your own fynk permissions via OAuth.

Advertise