How to Use the TfL MCP in LlamaIndex

Q: How does LlamaIndex manage TfL service disruptions?

You run getlinestatus and index the resulting disruption descriptions and reason codes. Later, your agent can query this knowledge base to understand systemic failure points or common delay causes on specific lines.

Q: What if I plan a multi-modal trip using TfL and LlamaIndex?

After running getjourney, you index the full result set. If a user asks about planning similar trips in the future, your system retrieves the precise combination of transfers, distances, and time estimates from the indexed data.

Q: Can LlamaIndex track road closures for TfL?

Yes. You can run getroaddisruptions and index the results. This makes it possible to query historical incidents, like 'What were the roadworks on the A4 last month?' The data stays searchable long after the initial API call.

Q: How is TfL stop point metadata handled by LlamaIndex?

When you run getstoppointdetails, the resulting rich metadata—like step-free access status and modes served—gets indexed. This allows your application to filter searches based on accessibility needs, rather than just location.

Index and query TfL data with LlamaIndex for knowledge-augmented insights.

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 LlamaIndex

Create your Vinkius account to connect TfL to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Persistent Trip Planning Knowledge

The `get_journey` tool plans a multimodal trip, returning detailed legs, fare estimates, and CO2 savings. By indexing this output, you create a knowledge base where historical journey data is searchable. You can query past trips to see what the best route was for that specific day's traffic patterns. Instead of just getting a single answer, LlamaIndex turns API results into documented facts for your RAG application.

Archived Service Status Data

`get_line_status` provides the current status (e.g., 'Minor Delays' or 'Suspended') for lines. Indexing this means you can query past service disruptions—for example, asking, 'What were the disruption details on the Jubilee Line last Tuesday?' The answer is grounded in historical API records. This capability moves beyond real-time checking; it creates a reliable history of transport performance.

Bike Network Mapping and Analysis

`get_bike_points` lists all docking stations, their coordinates, and total capacity. Indexing this data lets you build an internal map that tracks coverage gaps or areas where bike availability is historically low. You can query the network density across different boroughs. This turns a simple list of docks into strategic infrastructure intelligence.

Setup guide

Set up TfL MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all TfL MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to TfL tools.",
)
response = await agent.run("List recent TfL data")

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 LlamaIndex

You run `get_line_status` and index the resulting disruption descriptions and reason codes. Later, your agent can query this knowledge base to understand systemic failure points or common delay causes on specific lines.

After running `get_journey`, you index the full result set. If a user asks about planning similar trips in the future, your system retrieves the precise combination of transfers, distances, and time estimates from the indexed data.

Yes. You can run `get_road_disruptions` and index the results. This makes it possible to query historical incidents, like 'What were the roadworks on the A4 last month?' The data stays searchable long after the initial API call.

When you run `get_stop_point_details`, the resulting rich metadata—like step-free access status and modes served—gets indexed. This allows your application to filter searches based on accessibility needs, rather than just location.

This server touches public infrastructure data, including station IDs, geographic coordinates, and service type details. The indexed results are non-personal operational metrics for the London transport system.

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