How to Use the TfL MCP in Claude Code

Q: How do I plan automated journeys using TfL and Claude Code?

You run the getjourney tool, providing start and end coordinates. Your shell script captures multiple route options, including total duration and CO2 savings metrics, making it perfect for calculating efficiency reports in a pipeline.

Q: Can I check line status before running a deployment using TfL and Claude Code?

Yes. Use getlinestatus to query the current service state of any specific TfL line (e.g., Victoria Line). If the status is 'Suspended,' your script can immediately fail or execute a fallback plan.

Q: Does Claude Code handle bike data for last-mile planning?

You call getbikepoints to list all docking stations. This lets you integrate real-time cycle availability into your CI/CD environment, checking if enough bikes are available at a target location.

Q: What is the best way to search for locations using TfL and Claude Code?

Use getplacesearch with coordinates or keywords. This gives you place IDs, names, and categories—structured data that your script can then use to contextualize other API calls.

Script TfL operations using Claude Code via the MCP Server in CI/CD pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect TfL MCP to Claude Code

Create your Vinkius account to connect TfL to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup TfL with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Fetch real-time transport feeds.

Run `get_arrivals` to get predicted arrival times for any specific TfL stop point. This is ideal for running background jobs that constantly monitor service readiness. The output includes timestamps, line names, and vehicle IDs, making it easy to pipe this data into logging systems or triggering notifications in a CI pipeline.

Check London road conditions via MCP Server.

Execute `get_road_disruptions` from your script. You can filter by specific roads, letting the script check for incidents or planned works affecting delivery routes. The returned severity levels and alternative recommendations let you build robust failure detection logic into your deployment scripts.

Map out transport networks.

Use `get_modes` to list all available transport modes in the TfL network. This is essential for defining the full scope of a service or validating input types before running complex journey calculations. It provides structured data on whether your system needs to handle 'tube,' 'bus,' or 'river' services.

Setup guide

Set up TfL MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see tfl-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest TfL transactions." It will automatically discover and invoke the available TfL tools.

Terminal

claude mcp add --transport http tfl-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the TfL MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "tfl-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

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.

Connect TfL now

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 Claude Code

You run the `get_journey` tool, providing start and end coordinates. Your shell script captures multiple route options, including total duration and CO2 savings metrics, making it perfect for calculating efficiency reports in a pipeline.

Yes. Use `get_line_status` to query the current service state of any specific TfL line (e.g., Victoria Line). If the status is 'Suspended,' your script can immediately fail or execute a fallback plan.

You call `get_bike_points` to list all docking stations. This lets you integrate real-time cycle availability into your CI/CD environment, checking if enough bikes are available at a target location.

Use `get_place_search` with coordinates or keywords. This gives you place IDs, names, and categories—structured data that your script can then use to contextualize other API calls.

The server handles public infrastructure data: vehicle compliance details (ULEZ), road status, and station metadata. It never requires or accesses user credentials or private journey logs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript