How to Use the Mapflow MCP in Google ADK

Q: How do I configure Mapflow within a Google ADK workspace?

Use the McpToolset class to point your Google ADK agent to the Mapflow MCP server. The agent registers the tools dynamically, allowing Gemini models to call spatial extraction tasks directly.

Q: Can Google ADK and Mapflow trigger extractions automatically?

Yes, Google ADK triggers the createprocessing tool whenever your prompt requires geospatial feature extraction. The agent handles coordinate parsing and passes the correct JSON parameters to the server.

Q: How do Mapflow and Google ADK handle large-scale road mapping?

Your agent queries listmodels to locate the road extraction model, then creates a project via createproject. From there, it chunks the target region and runs parallel extraction jobs.

Feed automated vector data from satellite imagery straight into Google ADK enterprise pipelines using this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapflow MCP to Google ADK

Create your Vinkius account to connect Mapflow 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 Mapflow with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK satellite extraction pipelines

`create_processing` converts raw coordinate bounding boxes into clean GeoJSON vector layers containing detected buildings and roads. Your Gemini-powered agent triggers this operation to feed fresh spatial data directly into your analytical pipelines. Monitoring the pipeline is handled entirely through API calls. The agent tracks progress using `get_processing_status` and pulls the geometry coordinates with `get_processing_result` for downstream use.

Dynamic model selection with Mapflow MCP Server

`list_models` returns the current catalog of deep learning models optimized for specific infrastructure types. This lets your enterprise agent choose the right tool for detecting roads versus mapping forest canopies. This flexibility prevents extraction errors on complex terrain. Your pipeline queries the active models first, ensuring the payload sent to the API matches the target geographic feature.

Manage spatial assets with project workspaces

`create_project` instantiates logical containers to group your spatial processing runs. Your agent structures data by geographic sector, making long-term storage and tracking simple. Auditing these workspaces requires zero manual effort. The agent runs `list_projects` and `list_processings` to clear out stale runs and monitor processing volume across your organization.

Setup guide

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

Use the `McpToolset` class to point your Google ADK agent to the Mapflow MCP server. The agent registers the tools dynamically, allowing Gemini models to call spatial extraction tasks directly.

Yes, Google ADK triggers the `create_processing` tool whenever your prompt requires geospatial feature extraction. The agent handles coordinate parsing and passes the correct JSON parameters to the server.

Your agent queries `list_models` to locate the road extraction model, then creates a project via `create_project`. From there, it chunks the target region and runs parallel extraction jobs.

Yes, you can pass a specific list of tool names to the toolset parameter during initialization. This prevents the agent from running cost-heavy extraction tools when it only needs to check statuses.

All coordinate inputs and GeoJSON outputs pass through a secure, ephemeral V8 isolate on Vinkius. The raw spatial metadata is never cached or stored on the hosting platform, keeping your proprietary geographic coordinates private.

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