How to Use the Agro MCP in AutoGen

Q: How do I initialize Agro tools in AutoGen?

Call mcpservertools with a StreamableHttpServerParams object containing your Vinkius URL. Pass the resulting list directly to your AssistantAgent constructor.

Give your AutoGen agents the ability to debate agricultural strategies.

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 AutoGen

Create your Vinkius account to connect Agro to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate irrigation plans with live data

Agro connects your agents to real-world farming metrics. A weather agent pulls the forecast using `get_forecast_weather` while a soil agent checks current ground conditions via `get_current_soil`. They argue over whether to water the fields today or wait for tomorrow's rain. The system reaches a conclusion based on conflicting API inputs. If the UV index from `get_current_uvi` is extremely high, the conservation agent pushes to delay irrigation until evening. You watch the agents negotiate the optimal schedule before outputting a final recommendation.

Coordinate multi-agent polygon management

Defining land boundaries requires precision. One agent drafts coordinates and calls `create_polygon`, while a validator agent immediately runs `get_polygon` to verify the shape. If the area overlaps a restricted zone, the validator forces a correction. Managing updates happens through conversation. When a plot needs resizing, agents use `update_polygon` to adjust the boundaries. They then run `list_polygons` to ensure the entire farm layout remains logically consistent.

Analyze crop history via Agro MCP Server

Historical analysis involves parsing years of data. An analyst agent triggers `get_historical_weather` to build a climate profile, while a separate botanist agent calls `get_ndvi_history` to check vegetation health. They compare notes to find correlations between drought periods and low crop yields. Satellite imagery adds another layer to the debate. A scout agent uses `search_imagery` to find visual evidence of blight. The group synthesizes the weather logs, the NDVI charts, and the satellite metadata into a single actionable report.

Setup guide

Set up Agro MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Agro tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Agro_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Agro data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Agro_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Agro data")
    print(result.messages[-1].content)

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 AutoGen

Call `mcp_server_tools` with a `StreamableHttpServerParams` object containing your Vinkius URL. Pass the resulting list directly to your `AssistantAgent` constructor.

Yes. You can equip different agents with specific tools from the server. A climate agent might hold the weather functions while a mapping agent controls the polygon tools.

The adapter handles schema conversion automatically. Agents request weather or soil data naturally in conversation, and the framework executes the API calls in the background.

If a polygon lookup fails, the agent receives the error string. It then discusses the failure with the other agents and attempts a retry or requests different coordinates.

We route your bounding box parameters through a zero-trust execution layer. Vinkius drops the connection state the millisecond the satellite metadata returns, ensuring your areas of interest remain strictly confidential.

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