transport-nsw
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@transport-nswplan a trip from Sydney Central to Bondi Beach"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@pipeworx/transport-nsw
Journey planning, live departures, service alerts and commuter car-park occupancy for Sydney and the whole of New South Wales — trains, metro, buses, ferries and light rail.
Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.
Requires an API key — free and self-service at https://opendata.transport.nsw.gov.au/.
Platform key:
PLATFORM_TFNSW_KEYCaller-supplied:
_apiKeyargument on any tool
Tools
Tool | What it answers |
| Live departures from a stop, station or wharf |
| A full multi-leg journey from A to B |
| Current incidents and trackwork |
| Live park-and-ride occupancy |
Related MCP server: Transport NSW API Client MCP
Traps
The auth header is not a bearer token. It is literally the word apikey
followed by the key: Authorization: apikey abc123. Sending Bearer abc123
returns 401 with a message about "the calling application", which reads as a
bad key rather than a bad scheme — and sends you off rotating a key that was
fine.
The trip planner is EFA, not REST. /v1/tp/* is a hosted Mentz EFA
instance, so the parameters are EFA's (type_dm, name_dm, itdDate) and its
"no results" answer is HTTP 200 with a systemMessages array explaining
why — never an error status. efaComplaint() surfaces that message whenever
the result list is empty, because a silent empty journey list is otherwise
indistinguishable from "no trains run between these two places".
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"transport-nsw": {
"url": "https://gateway.pipeworx.io/transport-nsw/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/transport-nsw/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 1679+ 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/tfnsw_departures \
-H 'Content-Type: application/json' \
-d '{"stop_id":"200060"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/tfnsw_departures. 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": {
"transport-nsw": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-transport-nsw"]
}
}
}Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-transport-nswIt 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 Transport Nsw data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Provide real-time transportation data including bus arrivals, train service alerts, carpark availa…
Read-only public transit departures, stop search, and city coverage for bus and train users.
Get real-time NYC bus arrivals, live vehicle locations, and service alerts. Plan trips between any…
Stockholm transit: realtime departures, trip planning, disruptions and personal commute status.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThis server enables large language models to access and interact with real-time transport alerts from Transport for NSW's network, supporting filtering by transport mode and returning formatted alert information about disruptions and planned works.3 npm7MIT
- AlicenseBqualityDmaintenanceAn MCP service for interacting with Transport NSW's API that enables users to find transport stops around locations and retrieve information about transport alerts and disruptions.3MIT
- 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.388 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to access real-time Transport for London data, including tube/bus arrivals, line status, journey planning, and disruptions.1-