@pipeworx/la-metro

Routes, stops and live service cancellations for Los Angeles County Metro (LACMTA) bus and rail, from Metro's own open API at https://api.metro.net.

Part of Pipeworx — an MCP gateway connecting AI agents to 1865+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Keyless. No registration, no key, no quota published.

Tools

Related MCP server: mcp-transit-land

LA Metro has no public GTFS-Realtime feed — read this before adding a tool

The commonly cited api.metro.net/LACMTA/vehicle_positions, /trip_updates and /alerts paths are gone; all three return HTTP 404 (verified 2026-09-17). The Mobility Database lists LACMTA with static GTFS only and no realtime row at all.

The v2 API still advertises a "Real-Time data" tag over /{agency}/trip_detail/..., and that is the trap worth knowing about: those endpoints answer HTTP 200 with [] for every route, on both agencies, in the middle of a weekday afternoon. Fourteen bus and rail routes were swept at 15:00 PDT and every one came back empty. A tool built on them would pass every CI gate and quietly tell callers that LA Metro is not running any buses — the silent-zero failure class in docs/silent-zero-policy.md.

canceled_service_summary is live operational data and is wired up. It is the one real-time signal LACMTA publishes publicly, and it answers a question no schedule or GTFS feed can: is my line dropping trips today?

Agencies

LACMTA is the bus agency (~124 routes); LACMTA_Rail is rail and busway (A/B/C/D/E/K lines). The API returns HTTP 422 on any other value.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/la-metro/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_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 1865+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/lametro_routes \
  -H 'Content-Type: application/json' \
  -d '{"agency":"LACMTA","search":"Wilshire"}'

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

Run it from npm

@pipeworx/mcp-la-metro is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/la-metro/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "la-metro": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-la-metro"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

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 La Metro data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT