How to Use the Mapbox MCP in Google ADK

Q: Can I filter which Mapbox tools my Google ADK agent can use?

You can. When you initialize the McpToolset, you can pass an optional toolnames list. This restricts the agent to only the tools you specify, like 'geocode', 'getdirections', giving you firm control over its capabilities.

Connect Gemini to your logistics data. Use Google ADK and Mapbox to analyze routes, geocode addresses in BigQuery, and act on your data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapbox MCP to Google ADK

Create your Vinkius account to connect Mapbox 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 Mapbox with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Act on Your Data in BigQuery

Give your Gemini agent a direct line to your Google Cloud data. It can pull a list of customer addresses from a BigQuery table, then use the `geocode` tool to find coordinates for each one. No more manual export-import jobs. Once the addresses are geocoded, the agent can write the new coordinates back to BigQuery. Or, it can feed them straight into the `get_distance_matrix` tool to calculate a full delivery schedule, all within a single, autonomous workflow.

Reason Over Complex Spatial Problems

Gemini's large context window is a great match for the detailed data from Mapbox. You can feed it the entire JSON output from a `get_directions` call, and then ask it to analyze specific maneuvers or road segments. It can hold the whole route in its head. This also works for massive calculations. Give the agent a `get_distance_matrix` response for 50 different locations. It can hold the entire matrix in context to find not just the shortest path, but a path that meets other complex rules you define in your prompt.

Build with Your Google ADK MCP Server

This Mapbox MCP server plugs right into your Google Cloud environment. Add the `McpToolset` to your `LlmAgent` to give Gemini the ability to `search_nearby` for service depots or generate `get_isochrone` polygons for a territory analysis. Because it's all integrated, you can trigger these agents from Cloud Functions or run them on a schedule. You could, for instance, have a nightly agent use `get_elevation` to check terrain for new construction sites logged in a Cloud SQL database.

Setup guide

Set up Mapbox 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 Mapbox 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="Mapbox_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Mapbox 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 Mapbox. 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 Mapbox 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 Mapbox MCP in Google ADK

Your Gemini agent can query a location from BigQuery, pass the coordinates to the `get_isochrone` tool, and get back a polygon. It can then use that polygon data to update a different table or trigger another process, like a Looker Studio data refresh.

Yes, the tool definitions from the MCP Server tell the agent the exact format, like semicolon-separated "lon,lat" pairs for `get_directions`. Gemini is good at following these structured instructions, so you don't have to manually format the strings in your code.

You can. When you initialize the `McpToolset`, you can pass an optional `tool_names` list. This restricts the agent to only the tools you specify, like `['geocode', 'get_directions']`, giving you firm control over its capabilities.

This MCP Server is pre-built and managed by Vinkius. You don't write the API wrapper code, handle auth, or host it. You just point the `McpToolset` to the Vinkius URL, and your agent gets all eight Mapbox tools instantly.

The address strings or coordinate pairs you send to tools like `geocode` and `reverse_geocode` are processed in memory on Vinkius's zero-trust infrastructure. The data is passed to Mapbox for the API call and is not logged or stored by Vinkius.

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