How to Use the EOSDA MCP in AutoGen

Q: How do my AutoGen agents access the EOSDA tools?

You use the mcpservertools utility, providing your server URL. This function fetches the available tools, like getfields and renderindexmap, and makes them directly callable by any agent in your AutoGen conversation.

Q: What happens to my sensitive EOSDA data in an AutoGen conversation?

The data, like field names from getfields or moisture levels from getsoilmoisture, exists within the agent conversation history. The Vinkius MCP server itself is stateless, but you are responsible for securing the environment where your AutoGen agents are running and storing their logs.

Let your AutoGen agents debate agricultural strategy using live EOSDA data.

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 AutoGen

Create your Vinkius account to connect EOSDA 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 EOSDA with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Crop Strategy

Design a team of specialist agents that collaborate to manage your fields. One agent, the 'Agronomist', can be tasked with monitoring crop health by calling `get_ndvi_timeseries`. Another, the 'Irrigation Specialist', can use `get_soil_moisture` and `get_weather_forecast` to manage water resources. When the Agronomist detects a drop in NDVI, it alerts the group. The Irrigation Specialist then checks for water stress. They use shared data from the EOSDA MCP server to arrive at a conclusion. It's a conversation between experts, powered by real-time data.

Consensus-Driven Field Management

AutoGen's strength is letting agents challenge each other to find the best plan. Your 'Precision Ag' agent might generate a variable-rate fertilizer plan using `get_zoning_map`. But a 'Finance' agent can then calculate the cost and ask if a simpler, uniform application is more profitable. They debate, using data to back up their arguments. This process surfaces risks and trade-offs you might miss. Before applying expensive treatments, a 'Scout' agent could be dispatched to get fresh `get_satellite_imagery` to confirm the problem, preventing wasted resources. The final decision is a consensus, not a single command.

Automate Team Deliberation with AutoGen

You're not just building a tool-user; you're building a digital team. Define the roles, give them a shared goal, and provide them with this powerful MCP server. The agents will figure out how to use the tools to achieve the objective. A user's request to "plan the next growing season" could kick off a complex discussion. Agents would use `create_field` to define boundaries, pull historical trends with `get_evi_timeseries`, and analyze long-term forecasts from `get_weather_forecast` to propose a crop rotation plan. It's planning, automated.

Setup guide

Set up EOSDA 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 EOSDA 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="EOSDA_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent EOSDA 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="EOSDA_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent EOSDA 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 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 AutoGen

You use the `mcp_server_tools` utility, providing your server URL. This function fetches the available tools, like `get_fields` and `render_index_map`, and makes them directly callable by any agent in your AutoGen conversation.

Yes, that is the ideal workflow. You can have a 'Monitor' agent that periodically calls `get_ndmi_timeseries`. If it detects water stress, it can pass the specific field ID to a 'Dispatcher' agent, which then formulates an irrigation plan.

The key is good prompt engineering in your agent definitions. Clearly describe each agent's role and what tools it should prefer. For example, tell your 'Weather' agent that its primary tools are `get_weather_data` and `get_weather_forecast`.

Because agriculture is complex. A single agent might optimize for one variable, like vegetation index. AutoGen lets you build a team where one agent watches the budget, another watches the weather, and a third watches crop health. Their debate leads to more robust, resilient decisions.

The data, like field names from `get_fields` or moisture levels from `get_soil_moisture`, exists within the agent conversation history. The Vinkius MCP server itself is stateless, but you are responsible for securing the environment where your AutoGen agents are running and storing their logs.

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