
Connects Claude to the Washington Metropolitan Area Transit Authority's real-time and static data feeds for DC's Metro system. You'll need a free WMATA API key to use it. Hosted through Pipeworx's gateway, which means you can either connect to this specific server or access it alongside 673+ other data sources through their unified gateway endpoint. Includes an ask_pipeworx tool that lets you query transit data in plain English instead of calling specific endpoints directly. Useful when you're building transit apps, analyzing Metro schedules and routes, tracking train positions, or answering commuter questions about DC public transportation.
WMATA MCP — Washington Metro real-time + static data. Free API key (5k req/day).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
PLATFORM_WMATA_KEY. BYO: ?_apiKey=….rail_lines() — list rail linesrail_stations(line_code?) — list stations (optionally on a line)rail_station_info(station_code) — station inforail_predictions(station_codes) — next-train predictions (comma-sep codes; All for system-wide)rail_incidents() — current rail incidentsbus_routes() — list bus routesbus_route_details(route_id, date?) — route detailsbus_stops(lat?, lon?, radius?) — nearby bus stopsbus_predictions(stop_id) — bus arrival predictionsbus_incidents() — bus incidentshttps://api.wmata.com/...
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"wmata": {
"url": "https://gateway.pipeworx.io/wmata/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/wmata/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Wmata data" })
The gateway picks the right tool and fills the arguments automatically.
MIT