How to Use the EOSDA MCP in Google ADK

Q: How do I register the EOSDA tools within my Google ADK agent?

You initialize McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent tools parameter. This exposes all EOSDA capabilities, from weather forecasts to vegetation index trend tools, to your Gemini model.

Q: How does Google ADK handle large EOSDA weather datasets?

The ADK passes queries to getweatherdata to retrieve historical parameters like evapotranspiration and growing degree days. Gemini's massive context window processes these large JSON payloads without requiring pre-aggregation or truncation.

Q: Can I restrict which EOSDA tools my Google ADK agent can access?

Yes, you can use the optional toolnames filter in the ADK toolset configuration. This limits your agent to specific operations, like only allowing getsoilmoisture while blocking field creation tools.

Run enterprise-scale crop analysis by connecting Google ADK agents to EOSDA satellite indices and weather records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EOSDA MCP to Google ADK

Create your Vinkius account to connect EOSDA 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 EOSDA with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed EOSDA Satellite Data to Google ADK

The `get_satellite_imagery` tool allows Google ADK agents to query massive historical archives of Sentinel-2 and Landsat imagery for any monitored field. Gemini's million-token context window can ingest years of these raw image metadata records in a single turn, enabling deep historical trend analysis. Combining this historical imagery with your private farm records in BigQuery gives your enterprise agent complete context. Your agent can instantly correlate past yield maps with historical cloud-free satellite passes without hitting context limits.

BigQuery Integration with an MCP Server

This MCP Server connects your Google ADK pipelines to `get_weather_data`, pulling over 1800 weather parameters directly into your enterprise cloud workspace. Your Gemini agents can query historical soil temperature and precipitation data going back to 1979 to build predictive crop models. Storing these weather datasets alongside your spatial boundaries allows for automated regional risk assessments. You can prompt your agent to cross-reference `get_weather_forecast` with crop growth stages to flag frost risks across thousands of active fields simultaneously.

Precision Fertilizer Zoning via Vertex AI

The `get_zoning_map` tool generates detailed management zone boundaries that your Google ADK agent can parse to optimize nitrogen application rates. By analyzing these zones alongside physical soil profiles, your Vertex AI models can recommend target fertilizer blends for each specific zone. Visualizing these management zones is straightforward with the `render_index_map` tool. Your agent requests a rendered PNG map of the field, which can be stored directly in Google Cloud Storage for field operators to access on their mobile devices.

Setup guide

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

You initialize `McpToolset` with your Vinkius HTTP URL and pass it to your `LlmAgent` tools parameter. This exposes all EOSDA capabilities, from weather forecasts to vegetation index trend tools, to your Gemini model.

Absolutely, your agent can pull historical crop yields from BigQuery and match them with `get_ndvi_timeseries` outputs. This allows the Gemini model to analyze how canopy density changes affected final harvest metrics over multiple seasons.

The ADK passes queries to `get_weather_data` to retrieve historical parameters like evapotranspiration and growing degree days. Gemini's massive context window processes these large JSON payloads without requiring pre-aggregation or truncation.

Yes, you can use the optional `tool_names` filter in the ADK toolset configuration. This limits your agent to specific operations, like only allowing `get_soil_moisture` while blocking field creation tools.

Your field boundaries, crop types, and soil moisture metrics are transmitted over HTTPS directly to the EOSDA API. The transit occurs through a zero-trust V8 sandbox, ensuring your farm's proprietary spatial data is never leaked.

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