go-planning-mcp

go-planning-mcp

Enables LLMs to plan trips, check schedules, query live departures, and access 17 tools for GO Transit data via natural language.

Category
Visit Server

README

go-planning-mcp

An MCP server that wraps the Metrolinx GO Transit Open Data API, letting LLMs plan trips, check schedules, and query live departures through natural conversation. Self-hostable via Docker or deployable to Vercel in minutes.

Tools

17 tools, normalized to consistent snake_case DTOs (never a passthrough of Metrolinx's raw shapes). Full parameter tables and example output for every tool live in docs/TOOLS.md.

Tool Description
Trip planning
plan_trip Plan a trip by station/stop name (fuzzy-resolved) or code; composes cross-line transfers via Union automatically.
plan_journey Fine-control trip planner for exact stop codes — no fuzzy resolution, no transfer composition.
Stops
search_stops Fuzzy search for stops/stations by name fragment.
get_stop_details Location, service modes, facilities, parking, and accessibility for one stop.
get_next_service Live upcoming departures for one stop.
get_stop_destinations Where a stop's services go within a time window.
Schedules & lines
list_lines GO Transit's line roster for a service day, with valid direction codes.
get_line_schedule A line's published schedule for a service day (trip summaries, or times at one stop).
get_trip_status Live stop-by-stop status for a single trip.
Service updates
get_service_alerts Folded service/information/marketing alerts.
get_service_exceptions Today's cancelled trips and stops.
get_service_guarantee Service guarantee eligibility for a past trip.
get_union_departures Live Union Station departure board.
Fares & fleet
get_fares Fare rows between two stops, flattened by rider type and payment method.
get_fleet_consist The physical car makeup of a train, by trip or engine number.
Real-time (GTFS-RT)
get_vehicle_positions Live positions, delay, and occupancy for vehicles of one mode.
get_trip_updates What's off-plan right now — delays and cancellations.

Running your own server

Transport split: Claude Desktop → stdio; everything else → Streamable HTTP.

1. Get a Metrolinx API key

Register at the Metrolinx Open Data API registration form. It's free, but approval is manual and can take up to 10 business days.

2. docker run one-liner

docker run -e METROLINX_API_KEY=xxx -p 3000:3000 ghcr.io/emilsoleymani/go-planning-mcp

This serves the MCP endpoint at http://localhost:3000/mcp and a liveness probe at http://localhost:3000/health.

3. Compose quick start

git clone https://github.com/EmilSoleymani/go-planning-mcp.git
cd go-planning-mcp
cp .env.example .env  # then add your METROLINX_API_KEY
docker compose up

4. Claude Desktop (stdio)

{
  "mcpServers": {
    "go-transit": {
      "command": "npx",
      "args": ["go-transit-mcp"],
      "env": {
        "METROLINX_API_KEY": "your_key_here"
      }
    }
  }
}

From source (contributor/dev variant):

{
  "mcpServers": {
    "go-transit": {
      "command": "node",
      "args": ["dist/entry/stdio.js"],
      "env": {
        "METROLINX_API_KEY": "your_key_here"
      }
    }
  }
}

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured