How to Use the Navitia MCP in LlamaIndex

Q: How do I configure LlamaIndex to use the Navitia MCP Server?

Install llama-index-tools-mcp and instantiate a BasicMCPClient with the server URL. Pass it to McpToolSpec and convert it using totoollistasync() for your FunctionAgent.

Q: Can LlamaIndex cache the Navitia transit lines?

You can call getlines to pull the physical and commercial modes, then index the results. This prevents your agent from repeatedly hitting the API for static route configurations.

Q: How does LlamaIndex handle Navitia journey planning?

The planjourney tool returns highly structured JSON detailing transfers, walking distances, and fares. LlamaIndex parses this response into document nodes, allowing the user to query specific leg details semantically.

Q: Can I filter which Navitia tools my LlamaIndex agent uses?

Absolutely. Use the allowedtools filter when setting up the tool spec to restrict the agent to read-only queries like getarrivals or getdepartures.

Index European transit networks directly into LlamaIndex. Turn live train schedules and disruption alerts into a searchable RAG knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Navitia MCP to LlamaIndex

Create your Vinkius account to connect Navitia to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Navitia with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index timetables using this MCP Server

The `get_stop_schedule` tool extracts the complete weekday, weekend, and holiday service patterns for any transit stop. Your LlamaIndex application ingests this raw schedule data and embeds it into a vector store for fast semantic retrieval. When users ask about Sunday bus frequencies, the query engine searches the indexed timetable instead of hallucinating answers. You anchor your RAG application to actual transit reality.

Build a RAG system for transit coverage

The `get_networks` and `get_coverage` tools list every transit authority, coverage area, and operating line available in the API. You can dump this structural data into LlamaIndex to create a master directory of European transit systems. If a user asks which operators run the trams in Lyon, your agent pulls the exact authority names and data freshness indicators from the index. It grounds every response in the actual administrative data pulled from the source.

Embed active service alerts

The `get_disruptions` tool fetches live incident reports, strike impacts, and weather delays across the network. You can configure a LlamaIndex data pipeline to refresh this context periodically, keeping your knowledge base current. A query engine checking commuter routes will automatically retrieve these embedded disruption nodes. Your agent warns users about blocked lines by synthesizing the active incident descriptions directly from the vector store.

Setup guide

Set up Navitia 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 Navitia 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 Navitia tools.",
)
response = await agent.run("List recent Navitia 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 Navitia. 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 Navitia 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 Navitia MCP in LlamaIndex

Install `llama-index-tools-mcp` and instantiate a `BasicMCPClient` with the server URL. Pass it to `McpToolSpec` and convert it using `to_tool_list_async()` for your `FunctionAgent`.

You can call `get_lines` to pull the physical and commercial modes, then index the results. This prevents your agent from repeatedly hitting the API for static route configurations.

The `plan_journey` tool returns highly structured JSON detailing transfers, walking distances, and fares. LlamaIndex parses this response into document nodes, allowing the user to query specific leg details semantically.

Absolutely. Use the `allowed_tools` filter when setting up the tool spec to restrict the agent to read-only queries like `get_arrivals` or `get_departures`.

The system only receives latitude and longitude pairs or stop IDs to calculate distances. Vinkius runs the MCP Server in an ephemeral zero-trust environment, meaning your LlamaIndex data pipelines never expose coordinate history to third parties.

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