TFL MCP Server for Poke
Enables AI assistants to access real-time Transport for London data, including tube/bus arrivals, line status, journey planning, and disruptions.
README
TFL MCP Server for Poke
A Model Context Protocol (MCP) server providing Transport for London data to AI assistants like Poke.
Features
- Real-time arrivals at any Tube station or bus stop
- Line status for Tube, DLR, Overground, Elizabeth line
- Journey planning between any two locations
- Service disruptions and alerts
- Bus routes and bus stop search
- All TFL modes supported
Tools Available
| Tool | Description |
|---|---|
get_arrivals |
Real-time arrivals at a station/stop |
get_line_status |
Current status of TFL lines |
search_stops |
Find stations by name |
plan_journey |
Journey planning between locations |
get_line_stops |
All stops on a specific line |
get_disruptions |
Active service disruptions |
get_bus_routes |
List London bus routes |
search_bus_stops |
Find bus stops by name or location |
get_bus_arrivals |
Real-time bus arrivals at a stop |
Setup
1. Get a TFL API Key
- Go to api-portal.tfl.gov.uk/signup
- Create an account and verify your email
- Subscribe to the "500 requests per minute" plan (free)
- Copy your API key from your Profile
2. Local Development
# Clone the repository
git clone https://github.com/VJagiasi/tfl-mcp.git
cd tfl-mcp
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Set up environment
cp .env.example .env
# Edit .env and add your TFL_API_KEY
# Run the server
python src/server.py
The server will start at http://localhost:8000/mcp
3. Test with MCP Inspector
# In another terminal
npx @anthropic/mcp-inspector
Open http://localhost:3000 and connect to http://localhost:8000/mcp using "Streamable HTTP" transport.
Deployment to Render
One-Click Deploy
Manual Deploy
- Push this repo to GitHub
- Go to render.com and create a new Web Service
- Connect your GitHub repository
- Render will auto-detect
render.yaml - Add environment variable:
TFL_API_KEY= your API key - Deploy!
Your server will be available at: https://tfl-mcp.onrender.com/mcp
Connect to Poke
- Open Poke settings: poke.com/settings/connections/integrations/new
- Add MCP integration
- Enter your server URL:
https://tfl-mcp.onrender.com/mcp - Test it!
Example Queries
Once connected to Poke, try asking:
- "What's the status of the Victoria line?"
- "When's the next train at King's Cross?"
- "Plan a journey from Paddington to Heathrow"
- "Are there any disruptions on the Tube?"
- "Find bus stops near Trafalgar Square"
- "When's the next 73 bus?"
API Reference
This server uses the TFL Unified API. Key endpoints:
| Endpoint | Purpose |
|---|---|
/Line/Mode/{modes}/Status |
Line statuses |
/StopPoint/{id}/Arrivals |
Real-time arrivals |
/StopPoint/Search/{query} |
Search stations |
/Journey/JourneyResults/{from}/to/{to} |
Journey planning |
License
MIT
Disclaimer
This is not an official Transport for London (TFL) MCP server. It uses the publicly available TFL Unified API.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.