The TfL MCP Server exposes the TfL Unified API as tools for AI assistants to query live London transport data.
From the registry: Community-built server providing real-time London transport data via the TfL Unified API
Please install the `mcp-server-tfl` MCP server into my current AI client (that's you).
Optional prerequisites:
- TfL API Key (optional) — Optional — increases rate limits. Register at api-portal.tfl.gov.uk. (https://api-portal.tfl.gov.uk/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@oneill9/mcp-server-tfl"]
- optional environment variables:
- `TFL_APP_KEY`: TfL API key for higher rate limits. (example: `<your-api-key>`)
- `TFL_APP_ID`: TfL App ID (legacy API registrations). (example: `<your-app-id>`)
Note: Works without an API key at lower rate limits.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.TFL_APP_KEYTfL API key — register at api-portal.tfl.gov.ukMCP server for searching Airweave collections with natural language queries.