How to Use the TfL MCP in Windsurf
Build smart, multi-step workflows with Windsurf and the TfL MCP Server.
Works with every AI agent you already use
…and any MCP-compatible client
Connect TfL MCP to Windsurf
Create your Vinkius account to connect TfL to Windsurf — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.
Key Capabilities
Plan complex trips across London.
The `get_journey` tool plans a trip between two locations using all major TfL transport modes. It gives you full route options, showing total duration, CO2 savings, and how many transfers are involved. You tell your agent where you're going—say, from Paddington to Greenwich—and it figures out the best way to get there, providing detailed leg-by-leg instructions for tube, bus, walking, or cycling.
Check real-time arrivals at any stop.
Need to know when the next train is coming? The `get_arrivals` tool predicts arrival times for specific TfL stops. You just feed it a station ID and tell your agent what you're looking for, like 'Northern Line trains at Bank.' It returns predicted arrival times in minutes and exact timestamps, letting you coordinate transfers across the entire London network without guesswork.
Discover all stops and stations.
Don't know where to start your search? The `search_stop_point` tool finds matching TfL stop points by name or location. It gives you IDs, common names, what transport modes serve the spot, and its coordinates. This is perfect for when you need to find a station near an address, like 'find the tube station near Covent Garden,' so your agent can gather all the necessary details before running a plan.
Set up TfL MCP in Windsurf
Prerequisites
- Windsurf IDE installed (macOS, Windows, or Linux)
- Active Vinkius subscription with a valid endpoint token
- 1
Open MCP configuration
Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open
~/.codeium/windsurf/mcp_config.json. - 2
Add the TfL MCP
Paste the JSON snippet shown on the right into the
mcpServersobject. Replace[YOUR_TOKEN_HERE]with your endpoint token from cloud.vinkius.com. - 3
Refresh MCPs
Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
- 4
Verify in Cascade
Start a new Cascade conversation and ask something like "Show my TfL payment history." If connected, Cascade will call the TfL tools directly. You will see a green dot next to the server name in the MCP panel.
{
"mcpServers": {
"tfl-mcp": {
"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}
}
} Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by TfL. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
Real-time monitoring
Live
visibility into every interaction
Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.
Built-in savings
60%
lower AI costs
Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.
Single dashboard
One
place for every integration
Every tool your AI connects to, managed from a single screen. One account, complete control.
Common questions about TfL MCP in Windsurf
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the TfL MCP today
We host it, we monitor it, we maintain it. You just paste one token.