How to Use the Navitia MCP in Google ADK

Q: How does Google ADK analyze transit accessibility zones with Navitia?

Your agent invokes getisochrone to retrieve GeoJSON polygons representing reachable areas. Since Gemini handles massive token limits, it can process complex spatial coordinates and compare them with your internal location database.

Q: What tool should my agent use to resolve messy address strings?

Call searchplaces to run autocomplete-style searches on addresses, stations, and landmarks. This tool returns precise transit IDs and coordinates that your agent needs for routing.

Connect Google ADK agents to the Navitia MCP Server to run multi-modal routing queries alongside your BigQuery warehouse.

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 Google ADK

Create your Vinkius account to connect Navitia to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map transit accessibility using the Navitia MCP Server

`get_isochrone` generates GeoJSON polygons showing exactly how far a traveler can walk or ride from a specific coordinate within a set time limit. Your Gemini agent uses this spatial data to analyze real estate and job market accessibility. This tool exports raw geographic boundaries that map directly to your enterprise spatial data. You can feed these polygons straight into BigQuery for heavy-duty geographic analysis.

Fetch live departures for Gemini long-context analysis

`get_departures` pulls upcoming departures, scheduled timetables, and real-time delay indicators for any transit stop. Because Gemini models handle long context windows, you can feed entire station timetables into the prompt. The tool supports real-time data feeds from operators across France and Europe. Your agent parses this raw data to build live departure boards or monitor terminal performance.

Discover transit operator networks in any region

`get_networks` lists active transit operators, contributing authorities, and operational coverage areas in a targeted region. Your agent uses this tool to identify who runs the buses or trains before querying schedules. Pair this with `get_coverage` to validate region IDs like 'fr-idf' for Paris before executing deeper queries. This validation step keeps your pipeline from wasting API calls on unsupported territories.

Setup guide

Set up Navitia MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Navitia tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Navitia_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Navitia tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate the MCP toolset using the streamable HTTP parameters pointing to your Vinkius server URL. Pass this toolset object into the tools list when constructing your LlmAgent.

Yes, use the optional tool names filter in the toolset configuration to expose only specific endpoints. This prevents the agent from calling heavy analytical tools when it only needs simple schedules.

Your agent invokes `get_isochrone` to retrieve GeoJSON polygons representing reachable areas. Since Gemini handles massive token limits, it can process complex spatial coordinates and compare them with your internal location database.

Call `search_places` to run autocomplete-style searches on addresses, stations, and landmarks. This tool returns precise transit IDs and coordinates that your agent needs for routing.

Vinkius processes all coordinate queries through a secure, ephemeral V8 isolate sandbox. Your physical location queries are sent directly to the transit API and are never stored or logged on the Vinkius platform.

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