How to Use the Navitia MCP in AutoGen

Q: How do I initialize the Navitia MCP Server in AutoGen?

Install autogen-extmcp and use mcpservertools with the StreamableHttpServerParams. Pass the resulting tools list directly into your AssistantAgent constructor.

Q: Can AutoGen agents analyze Navitia isochrone data?

Yes. One agent can call getisochrone to generate the reachable area polygons. Another agent can parse the GeoJSON boundaries to debate which neighborhoods fit a commuter's criteria.

Build debating transit agents with AutoGen. Let specialized AI workers negotiate multimodal journeys and verify real-time disruptions.

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 AutoGen

Create your Vinkius account to connect Navitia to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate routing options with AutoGen

The `plan_journey` tool calculates complex multimodal itineraries across Europe. You can assign this tool to a dedicated routing agent, while a separate accessibility agent reviews the output for wheelchair-friendly transfers. These agents debate the trade-offs between walking distances and total travel time. The routing agent might suggest a faster trip, but the accessibility agent forces a recalculation if the intermediate stops lack elevator access.

Cross-check schedules via MCP Server

The `get_departures` and `get_disruptions` tools feed live station data and incident reports into your AutoGen workspace. A monitoring agent constantly polls these endpoints to verify the viability of a planned route. If the monitor detects a strike via the disruption tool, it alerts the routing agent to find an alternative. They negotiate a new path using different transit networks before presenting the final consensus to the user.

Resolve ambiguous stops collaboratively

The `search_places` and `get_nearby_stops` tools handle geographic discovery and address resolution. A geocoding agent uses these to translate user text into exact transit nodes. If a user asks for a station near a specific monument, the geocoding agent pulls the coordinates and passes them to a scheduling agent. The scheduling agent then calls `get_arrivals` to build a complete picture of the local transit situation.

Setup guide

Set up Navitia MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Navitia tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Navitia_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Navitia data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Navitia_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Navitia data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with the `StreamableHttpServerParams`. Pass the resulting tools list directly into your `AssistantAgent` constructor.

Yes. One agent can call `get_isochrone` to generate the reachable area polygons. Another agent can parse the GeoJSON boundaries to debate which neighborhoods fit a commuter's criteria.

The conversational framework handles context sharing automatically. When one agent calls `get_networks` to list transit authorities, the output enters the chat history for the rest of the swarm to reference.

You enforce this through system prompts. Instruct the agent to always validate the region ID against `get_coverage` before attempting to pull lines or schedules.

No. The MCP Server processes routing parameters like walking speed or wheelchair requirements entirely in memory. Vinkius destroys the sandbox after execution, ensuring your multi-agent debates leave no persistent data trails.

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