How to Use the Agro MCP in Google ADK

Q: How do I integrate the Agro toolset with a Gemini agent using Google ADK?

You import McpToolset and StreamableHttpServerParameters from the ADK library. Point it to your Vinkius URL for the Agro server, then pass the resulting toolset into the tools list when you initialize your LlmAgent.

Q: Can my Google ADK agent analyze satellite imagery from the Agro server?

Yes. The agent can use the searchimagery tool to find available satellite photos for an area. It can also get processed data like historical vegetation indexes by calling getndvihistory.

Connect Gemini to live agricultural data. Use Google ADK to analyze field metrics from satellite imagery, weather, and soil sensors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agro MCP to Google ADK

Create your Vinkius account to connect Agro 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 Agro with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Field Data into BigQuery

Your Gemini agent can now act as the bridge between the field and your data warehouse. Use the Agro toolset to pull historical soil data (`get_historical_soil`) or satellite vegetation indexes (`get_ndvi_history`) for a specific farm. The agent gets this data and can then pipe it directly into a BigQuery table for large-scale analysis. This setup allows for more than just a data dump. Because Google ADK is built for Gemini, your agent can use its huge context window to summarize findings from years of data pulled from the MCP server. It can compare historical yields from your database with weather patterns from the Agro tools to find correlations you might have missed.

Build Enterprise Agents on Google ADK

The Agro MCP server exposes all its operations as a single `McpToolset` in your Google ADK project. This means your agent can manage field boundaries (`create_polygon`, `list_polygons`) and query real-time conditions (`get_current_weather`) using the same framework you already use for your other Google Cloud services. You can also use the `tool_names` filter when creating the toolset to restrict which tools are exposed. This lets you build specialized agents—one for meteorology using only the weather tools, another for geodesy using only the polygon tools—all running on your managed Vertex AI endpoints.

Forecast and Plan with Gemini

Start making proactive decisions instead of just reacting. Your agent can call `get_forecast_weather` and `get_forecast_uvi` to get a clear picture of the week ahead. It can then combine this with your own operational data to suggest optimal planting or harvesting windows. The real advantage is combining the Agro server's external data with your internal data in Google Cloud. An agent could check a weather forecast, cross-reference it with soil moisture history from `get_historical_soil`, and then check a BigQuery table of scheduled irrigation to prevent overwatering.

Setup guide

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

You import `McpToolset` and `StreamableHttpServerParameters` from the ADK library. Point it to your Vinkius URL for the Agro server, then pass the resulting toolset into the `tools` list when you initialize your `LlmAgent`.

Yes. The agent can use the `search_imagery` tool to find available satellite photos for an area. It can also get processed data like historical vegetation indexes by calling `get_ndvi_history`.

The native integration is the key. Your agent can pull data from the Agro server and immediately use it with other Google services like BigQuery and Vertex AI. You don't have to build any complex data pipelines or custom connectors.

Definitely. Google ADK is designed for building agents that can be deployed on Google Cloud. You can set up your agent as a persistent service on Vertex AI or Cloud Run to perform background monitoring tasks using the Agro tools.

The server only processes geographic coordinates for polygons and their related agricultural data (weather, soil, etc.). It never sees your Google Cloud credentials or other project data. Vinkius isolates each request in a sandboxed environment and uses a unique token for authentication, keeping your farm's operational data separate.

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