MBTA Worcester Line MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MBTA Worcester Line MCP Server
An MCP (Model Context Protocol) server that provides real-time train schedule information for the MBTA Worcester Line. Built with Next.js and deployable on Vercel.
Features
Real-time train departures from any Worcester Line station
Merges scheduled times with live predictions
Supports all 18 Worcester Line stops
Works with Gemini CLI and other MCP clients
Related MCP server: MBTA MCP Server
Quick Start
1. Get an MBTA API Key
Get a free API key at: https://api-v3.mbta.com
2. Install Dependencies
npm install3. Configure Environment
Copy .env.example to .env.local and add your MBTA API key:
MBTA_API_KEY=your-mbta-api-key-here
MCP_API_KEY=your-secret-token # Optional: for authentication4. Run Locally
npm run dev5. Test the MCP Server
npm run test:mcpDeployment
Deploy to Vercel
Push to GitHub
Import to Vercel
Add environment variables:
MBTA_API_KEY: Your MBTA API keyMCP_API_KEY: Secret token for authentication (optional)
Client Configuration
Gemini CLI
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"mbta": {
"httpUrl": "https://your-app.vercel.app/api",
"headers": {
"Authorization": "Bearer YOUR_MCP_API_KEY"
},
"timeout": 30000
}
}
}Or via CLI:
gemini mcp add --transport http mbta https://your-app.vercel.app/apiClaude Desktop (via mcp-remote)
{
"mcpServers": {
"mbta": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://your-app.vercel.app/api/mcp"]
}
}
}Available Tools
get_worcester_departures
Get upcoming train departures from any Worcester Line station.
Parameters:
Name | Type | Required | Description |
| string | Yes | Stop name or ID (e.g., "South Station", "framingham") |
| string | No | "outbound" (toward Worcester) or "inbound" (toward Boston). Default: "outbound" |
| string | No | Date in YYYY-MM-DD format. Default: today |
| number | No | Number of departures (1-20). Default: 5 |
Example queries:
"What trains leave South Station for Worcester?"
"Get next trains from Framingham to Boston"
"What trains leave Westborough tomorrow morning?"
Worcester Line Stops
South Station, Back Bay, Lansdowne, Boston Landing, Newtonville, West Newton, Auburndale, Wellesley Farms, Wellesley Hills, Wellesley Square, Natick Center, West Natick, Framingham, Ashland, Southborough, Westborough, Grafton, Worcester
Project Structure
src/
├── app/
│ ├── api/[transport]/route.ts # MCP handler
│ └── page.tsx # Status page
├── lib/
│ ├── mbta/
│ │ ├── client.ts # MBTA API client
│ │ ├── types.ts # TypeScript types
│ │ └── stops.ts # Stop ID mappings
│ └── mcp/
│ ├── auth.ts # Authentication
│ └── tools/ # MCP tools
│ ├── get-departures.ts
│ └── index.tsLicense
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Omio MCP server for ChatGPT, Claude and any AI agent: search trips, find the cheapest day and start booking in your own Omio account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Omio yourself; Cotlet does not store your password and you need no Omio API key. About the official Omio API: Omio has no public API for your own account (checked 24 Oct 2026). Its affiliate programme lists a Search API for partners, and its app in ChatGPT searches trips; Your Bookings, saved travelers and checkout work only on omio.com and in the Omio app. Setup and FAQ: https://cotlet.dev/integrations/omio-api-mcp-server
tri-train is a training platform for triathletes that syncs activities from Strava and Garmin and exposes them to Claude through a remote MCP server. Ask Claude how your last block went, why your run pace dropped, or whether you are fresh enough for Sunday's race, and it answers from your real data: activities with laps and grade-adjusted pace, weekly load and the performance management chart (CTL/ATL/TSB), sleep, HRV and resting heart rate, and your race calendar with predictions. Claude can also act: create and adjust planned workouts with structured intervals, push them to your Garmin watch, add races and write notes. Every change is journaled and can be undone. Read and write access are separate OAuth scopes, and the server enforces them on every call. Built and hosted in Switzerland by a triathlete; data stays on our own servers (Swiss revDSG / GDPR).
A real clock for AI agents: current time, timezone conversion, and DST facts from the IANA tzdb.
BusCalc 1.8.0 exposes 33 public tool families: 26 calculations and seven attributed data lookups. Calculate business pricing, finance, uncertainty, lease economics and emergency dispatch margins. Look up metals, energy, exchange rates, weather, BLS, USDA, Census and selected emergency sources, including NOAA gauges and USGS flood-impact points. Calculations include unsigned replayable receipts. Lookup results include source and observation dates where available. Road and outage coverage varies by location. The public Streamable HTTP endpoint is https://buscalc.com/api/mcp. Direct access is anonymous and rate limited. Full guide: https://buscalc.com/for-ai/
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables users to interact with Washington DC Metro (WMATA) transit system through natural language queries. Provides real-time train arrivals, service alerts, station information, trip planning, and accessibility updates.2,969 npmMIT
- AlicenseBqualityFmaintenanceEnables AI clients to access Boston's MBTA public transit data, including real-time predictions, schedules, route planning, and service alerts.321Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables real-time Indian Railways information retrieval, including live train running status, station schedules, and upcoming arrivals/departures.ISC
- AlicenseNot gradedqualityBmaintenanceProvides real-time San Francisco Bay Area Rapid Transit data, enabling queries about BART schedules, routes, and station information through natural language.129 npmMIT