mcpField
C
Cta

Cta

Remote
pipeworx.ioMaps & Travel0Updated 4d ago

About Cta

Cta is an MCP server for Chicago transit information, providing real-time arrival predictions and vehicle locations for CTA 'L' trains and buses. It can connect through the Pipeworx gateway or run locally over stdio.

Key features

  1. 01Get 'L' train arrival times
  2. 02View live train positions by line
  3. 03Get bus stop arrival predictions
  4. 04View live bus positions by route

Use cases

  1. 01Check the next train at a station
  2. 02Locate trains on an 'L' line
  3. 03Find bus arrivals by stop or intersection
  4. 04Track buses running on a route

MCP support

It exposes tools for CTA train and bus arrival predictions and live positions to MCP clients. It supports the Pipeworx gateway as well as local stdio execution.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/cta/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-cta

CTA MCP — Chicago Transit Authority real-time trains ('L') + buses

Part of Pipeworx — an MCP gateway connecting AI agents to 1875+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
cta_train_arrivalsReal-time Chicago CTA 'L' train arrivals at a station — answers "when is the next train Chicago", next Red Line at Belmont, Blue Line to O'Hare from Clark/Lake. Returns each upcoming train's line color, destination, arrival time and minutes_away, plus approaching / delayed / scheduled-only flags and the platform description. Station accepts a name ("Belmont", "Clark/Lake", "O'Hare") or a 5-digit mapid (e.g. 41320). Example: cta_train_arrivals({ station: "Belmont", route: "Red" })
cta_train_positionsLive Chicago CTA 'L' train positions on one or more lines — where every Red Line, Blue Line, Brown, Green, Orange, Purple, Pink, or Yellow train is right now: lat/lon, heading, next station with ETA, destination, approaching and delayed flags. Answers "where are the Blue Line trains" for the Chicago L. Example: cta_train_positions({ routes: "Red,Blue" })
cta_bus_predictionsChicago CTA bus tracker arrival predictions at a bus stop — route, destination, predicted minutes until arrival ("DUE" = arriving now), delay flag, and vehicle id. Pass stop_id (the 4-5 digit stop number posted on CTA bus-stop signs), optionally with route. If you only know the stop by name, pass route + find_stop (a street/intersection fragment like "clark & madison") and the stop is looked up for you. Example: cta_bus_predictions({ route: "22", find_stop: "addison" })
cta_bus_positionsLive Chicago CTA bus positions on a route — every vehicle currently running: lat/lon, heading, destination, delayed flag, and distance along the pattern. Answers "where is the 22 Clark bus right now" via the CTA bus tracker. Example: cta_bus_positions({ route: "22" })

Quick Start

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

{
  "mcpServers": {
    "cta": {
      "url": "https://gateway.pipeworx.io/cta/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/cta/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 1875+ 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/cta_train_arrivals \
  -H 'Content-Type: application/json' \
  -d '{"station":"Belmont","route":"Red"}'

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

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-cta

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Cta data" })

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

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.