How to Use the Agro MCP in Pydantic AI

Q: What's the setup for using the Agro MCP toolset with Pydantic AI?

It's minimal. After you pip install 'pydantic-ai-slimmcp', you create an MCPToolset instance with your Vinkius server URL. Then you just pass this into the toolsets list when you create your Agent.

Get type-safe agricultural data in your Python app. Pydantic AI validates every response from the Agro server so you can build with confidence.

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 Pydantic AI

Create your Vinkius account to connect Agro to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Validated Farm Data, Guaranteed

The Agro server provides tools for weather, soil, and satellite data. When you use it with Pydantic AI, every single response is automatically validated against a Pydantic model. If the API ever returns malformed data, your code raises a `ValidationError` immediately. This means no more silent failures or corrupted data in your application. When you ask for the current weather with `get_current_weather`, you aren't just getting a dictionary. You're getting a Pydantic object you can trust, with types that your IDE and static analysis tools can understand.

Model-Agnostic Agent Development

Pydantic AI lets you choose your LLM. You can use the Agro tools with OpenAI, Anthropic, Gemini, or a local model. The logic for calling tools like `create_polygon` or `get_ndvi_history` stays exactly the same; you just swap out the LLM backend. This approach frees you from vendor lock-in. You can prototype with a fast, cheap model and then switch to a more powerful one for production without rewriting your core application logic. The `MCPToolset` integrates directly into the Pydantic AI `Agent`, making this MCP Server a portable part of your stack.

Build Reliable Agri-Tech with Pydantic AI

Your agent can manage a whole portfolio of fields. Use `list_polygons` to get all your monitored areas, then loop through them to get fresh data using `get_current_soil` or `get_accumulated_precipitation`. Pydantic AI ensures the data for each field is correct before your code even sees it. This focus on correctness is critical in agri-tech. Misinterpreting a soil moisture reading or a temperature forecast can have real-world consequences. By using an MCP Server with Pydantic AI, you build a system that prioritizes data integrity, which helps prevent bugs caused by unexpected API outputs.

Setup guide

Set up Agro MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "agro-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Agro tools.",
)

result = await agent.run("List recent Agro transactions")
print(result.output)

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 Pydantic AI

Pydantic AI generates models from the MCP server's schema. When your agent calls an Agro tool, the JSON response is parsed and validated against that model. If anything is missing or has the wrong type, it raises an error instead of letting bad data into your app.

It's minimal. After you `pip install 'pydantic-ai-slim[mcp]'`, you create an `MCPToolset` instance with your Vinkius server URL. Then you just pass this into the `toolsets` list when you create your `Agent`.

Absolutely. Pydantic AI is model-agnostic. You can configure it to use any LLM that has a compatible adapter, including models running locally, while still using the hosted Agro server for its specialized tools.

If the server returns an error, Pydantic AI passes that exception to your code. If the server returns a successful but malformed response—like a string where a number is expected—Pydantic AI raises a `ValidationError`, stopping the bad data cold.

The server only ever sees the inputs for the tools you call, like polygon coordinates or dates for historical queries. Your LLM provider, API keys, and application code are never exposed. Vinkius uses token-based authentication, and every request to the MCP server runs in a completely isolated sandbox.

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