Skip to main content
Glama

mcp-bart

BART MCP — San Francisco Bay Area Rapid Transit real-time data (api.bart.gov)

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Tools

Tool

Description

bart_departures

Real-time BART San Francisco Bay Area train departures for a station — next train departure times in minutes, per destination, with platform, direction, train length (cars), line color, delay, and bikes allowed. Station accepts a 4-letter BART code ("EMBR", "SFIA") or a station name ("Embarcadero", "Downtown Berkeley", "SFO"). Answers "when is the next BART train". Example: bart_departures({ station: "Embarcadero" })

bart_stations

List all 50 BART San Francisco Bay Area train stations with 4-letter code, full name, city, street address, and coordinates. Optional filter matches station name or city (e.g. "Oakland", "Berkeley", "airport"). Use to find the station code for departures, trips, or fares. Example: bart_stations({ filter: "San Francisco" })

bart_trip_planner

Plan a BART trip between two Bay Area stations — the next trains from origin to destination with departure and arrival times, trip duration, legs (line, transfer stations, bikes), and the fare (Clipper and discount prices). Covers trips like SF to Oakland, Embarcadero to SFO airport, Berkeley to Millbrae. Stations accept 4-letter codes or names. Example: bart_trip_planner({ from: "Embarcadero", to: "SFIA" })

bart_advisories

Current BART service advisories and delays for the San Francisco Bay Area train system, plus elevator outage status at stations. Answers "is BART delayed right now", "are there BART service alerts", "which BART elevators are out". Example: bart_advisories({})

Related MCP server: Bay Wheels MCP Server

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "bart": {
      "url": "https://gateway.pipeworx.io/bart/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/bart/mcp returns the tools in the table above plus the shared Pipeworx meta-toolsask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1476+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Bart data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/bart_departures \
  -H 'Content-Type: application/json' \
  -d '{"station":"EMBR"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/bart_departures. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables 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.
    458 npm
    MIT
  • F
    license
    A
    quality
    C
    maintenance
    Provides read-only access to live Bay Area transit data, including routes, stops, real-time departures, vehicle positions, and service alerts, for use by large language models.
    6
    -