TfNSW Realtime Alerts MCP Server
LocalAbout TfNSW Realtime Alerts MCP Server
TfNSW Realtime Alerts MCP Server connects AI assistants to Transport for NSW's real-time alerts for disruptions and planned works. It offers mode-filtered alerts and a structured prompt for summarizing major disruptions.
Key features
- 01Retrieve current transport alerts
- 02Filter alerts by transport mode
- 03View affected routes, periods, and impacts
- 04Provide a disruption-summary prompt
Use cases
- 01Check current alerts for a transport mode
- 02Review routes affected by planned works
- 03Summarize major network disruptions
MCP support
The MCP server exposes TfNSW real-time transport alerts as a tool and resources, with filtering by transport mode. It also provides a prompt for summarizing major disruptions; a TfNSW Open Data API key is required.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y tfnsw-realtime-alerts-mcp-serverNSW_TRANSPORT_API_KEYSecretLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
1Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| mode | enum | Yes | Transport mode to get alerts forall | buses | ferries | lightrail | metro | nswtrains | regionbuses | sydneytrains |
Details
From the project READMETfNSW Realtime Alerts MCP Server
A Model Context Protocol server for Transport for NSW's (TfNSW) Realtime Alerts API. This server provides tools to access and interact with real-time transport alerts and information via Large Language Models.
Overview
This TypeScript-based MCP server implements integration with Transport for NSW's Realtime Alerts system. It enables AI assistants to access up-to-date information about transport disruptions, planned works, and other important alerts across the NSW transport network.
Features
Resources
- List and access transport alerts via
nsw-transport://URIs - Filter alerts by transport mode (buses, trains, ferries, etc.)
- Plain text format for easy consumption by AI assistants
Tools
get-transport-alerts- Retrieve current transport alerts- Filter by transport mode
- Returns formatted alert information including affected routes, time periods, and impact details
Prompts
transport-disruption-summary- Generate a summary of current transport alerts- Includes relevant alert details as embedded resources
- Returns structured prompt for LLM summarisation of major disruptions
Transport Modes
The following transport modes are supported:
all- All transport modesbuses- Sydney Metro and Outer Metro Bus servicesferries- Sydney Ferries and Newcastle Transport ferrieslightrail- Light Rail servicesmetro- Sydney Metronswtrains- NSW Trains regional trains and coachesregionbuses- Regional Bus servicessydneytrains- Sydney Trains suburban and intercity network
Authentication
This server requires authentication with the TfNSW Open Data API. You will need to register for an API key at the TfNSW Open Data Hub.
Installation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"tfnsw-realtime-alerts": {
"command": "npx",
"args": [
"-y",
"tfnsw-realtime-alerts-mcp-server"
],
"env": {
"NSW_TRANSPORT_API_KEY": "your_api_key_here"
}
}
}
}
Replace "your_api_key_here" with your TfNSW API key from the TfNSW Open Data Hub.
Development
Configure your API key as an environment variable in your .env file:
NSW_TRANSPORT_API_KEY="your_api_key_here"
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Debugging
You can use the MCP Inspector for debugging, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
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.