How to Use the Mapillary MCP in Google ADK

Q: How do I configure the Mapillary MCP Server inside Google ADK?

Install google-adk and set up McpToolset with the server URL. Pass that toolset to your LlmAgent initialization. You can use the toolnames filter if you only want to expose specific endpoints.

Feed massive street-level datasets into Gemini using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapillary MCP to Google ADK

Create your Vinkius account to connect Mapillary 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 Mapillary with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run the Mapillary MCP Server with Gemini's massive context

Google ADK lets you dump an absurd amount of data into your agent's context window. You connect this MCP server using the `McpToolset` class. From there, your Gemini model can ingest thousands of map features and actually remember them. The agent calls `search_images` across a massive city grid. It pulls back hundreds of image IDs, coordinates, and capture dates. Because Gemini handles over a million tokens, it can cross-reference all those `get_image` results against your existing BigQuery datasets without breaking a sweat.

Cross-reference traffic sign detections with enterprise data

Road infrastructure analysis requires context. Your agent uses `get_map_features` to pull a massive inventory of traffic signs and road objects. You can then write an agent loop that compares these real-world detections against municipal records stored in Vertex AI. If a specific sign looks out of place, the model digs deeper. It runs `get_image_detections` on the exact photo to check the geometry and confidence scores. You get a system that validates physical infrastructure against your database automatically.

Analyze miles of road sequences in one shot

Tracking road conditions means looking at routes, not just isolated points. The agent triggers `search_sequences` to find every mapped path through your target bounding box. It then feeds those sequence IDs directly into `get_sequence` to map out the entire drive. It can then call `get_detection_value` for specific objects along that route. You build an enterprise workflow that audits miles of street-level imagery, all managed through Google Cloud infrastructure.

Setup guide

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

Install `google-adk` and set up `McpToolset` with the server URL. Pass that toolset to your `LlmAgent` initialization. You can use the `tool_names` filter if you only want to expose specific endpoints.

Gemini's massive context window. You can pull thousands of results from `search_images` and `search_sequences` and the model will actually retain the coordinates for complex reasoning.

Yes. If you only want your agent checking specific items, use the `tool_names` argument. You can expose `get_image_detections` while hiding the broader search endpoints.

The agent pulls raw GPS coordinates and image metadata straight from the API. You can then instruct your Gemini agent to format those `get_map_features` results and write them directly into BigQuery.

The server processes your bounding box coordinates, sequence IDs, and compass angles. The Vinkius zero-trust architecture ensures every request runs in an isolated, memory-only container that is destroyed immediately after your Gemini agent gets its response.

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