Bring Public Transport
to OpenAI Agents SDK
Learn how to connect Transport for London to OpenAI Agents SDK and start using 11 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for Subscribers
What is the Transport for London MCP Server?
Connect to Transport for London (TfL) and access real-time London transit data through natural conversation — no API key needed.
What you can do
- Tube Status — Check real-time status of all Underground lines (Good Service, Minor/Severe Delays, Suspended)
- Line Details — Get detailed info about any tube, overground, DLR, Elizabeth line or tram route
- Bus Arrivals — Get live bus arrival predictions for any stop
- Journey Planning — Plan journeys between any two London locations with step-by-step directions
- Road Status — Check major road status and disruptions across London
- Bike Points — Find Santander Cycle docking stations with bike and dock availability
- Stop Search — Search for bus stops, tube stations and river piers by name
How it works
1. Subscribe to this server
2. No API key needed — TfL API is free and open
3. Start exploring London transit data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- London Commuters — check tube status, plan journeys and find bus arrivals in real-time
- Tourists — navigate London's transport system with live arrival data and journey planning
- Developers — integrate TfL transit data into apps and travel tools
Built-in capabilities (11)
Returns predicted arrival times, destination, line number, vehicle ID and expected time to station. Use the stop point ID (e.g. "490009056W") from search_stop. Get live arrival predictions for a bus stop
Get detailed info for a specific bike docking station
Returns bike availability, dock availability, station locations and status. Useful for finding nearby bikes for cycling journeys. Search for Santander Cycle (Boris Bike) docking stations
Returns multiple route options with estimated duration, walking distance, fare cost, number of changes and step-by-step directions. Input locations can be station names, addresses or postcodes. Plan a journey between two points in London
Supports tube, overground, DLR, Elizabeth line, tram and river bus lines. Get detailed information about a specific TfL line
Returns the ordered list of stations the line serves. Useful for understanding the full journey path of a tube line. Get the route sequence for a TfL line
Shows whether each line has Good Service, Minor Delays, Severe Delays, or is Suspended/Part Suspended. If no line IDs specified, returns all tube lines. Use line_ids to check specific lines (comma-separated, e.g. "central,victoria,northern"). Get real-time status for TfL tube lines
Returns disruption details with severity, location, cause and estimated clearance times. Get current road disruptions in London
Shows whether roads have Good, Minor or Severe congestion. Get status of London major roads
Useful for identifying the correct stop ID for arrival queries. Get details for a specific bus stop or station
Returns matching stops with their IDs, locations, modes and routes. Use the returned IDs with get_arrivals or get_stop_details. Search for bus stops and stations by name
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 11 tools from Transport for London through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Transport for London, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Transport for London in OpenAI Agents SDK
Transport for London and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Transport for London to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Transport for London in OpenAI Agents SDK
The Transport for London MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Transport for London for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Transport for London MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Do I need an API key?
No! TfL's Unified API is completely free and open. No authentication required.
What transport modes are covered?
TfL covers: Tube (Underground), Overground, DLR, Elizabeth line, Tram, Bus, River Bus, Santander Cycles (Boris Bikes) and major roads across London.
Can I plan a journey between two locations?
Yes! Use get_journey with origin and destination (station names, addresses or postcodes). Returns multiple route options with duration, changes, walking distance and step-by-step directions.
Can I check live bus arrivals?
Yes! First use search_stop to find the stop ID by name, then use get_arrivals with that stop ID to get real-time bus arrival predictions.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.