How to Use the MAPA (Agricultura) MCP in OpenAI Agents SDK

Q: How do I connect MAPA (Agricultura) to OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance pointing to the Vinkius MCP Server endpoint. Pass it to your agent's mcpservers array.

Q: Can the OpenAI Agents SDK cache MAPA (Agricultura) tools?

Yes. Set cacheToolsList=True when initializing the server connection. This stops the agent from reloading the 8 tool definitions every time it boots.

Q: Which MAPA (Agricultura) search tools does the OpenAI Agents SDK support?

The agent automatically discovers searchpackages. You can pass queries like "agrofit" or "organization:mapa" directly through your conversational prompts.

Q: How do I handle rate limits from the Brazilian government portal?

Implement retry logic in your agent's guardrails. If a getresource call fails due to throttling, the SDK can catch the error and queue a delayed retry.

Fetch Brazilian agricultural data directly into your OpenAI Agents SDK pipelines with built-in guardrails and full execution tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MAPA (Agricultura) MCP to OpenAI Agents SDK

Create your Vinkius account to connect MAPA (Agricultura) to OpenAI Agents SDK 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 MAPA (Agricultura) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe MAPA (Agricultura) MCP Server integration

This MCP Server connects your OpenAI agents to the Brazilian Ministry of Agriculture's open data portal. When your agent calls `search_packages` to find agrofit records, the SDK validates the request against your custom guardrails before executing the external call. You get full visibility into the API traffic. Every time a specialized agent hits `get_resource` to pull rural inspection metadata, the OpenAI dashboard traces the exact payload. If the government API changes its schema, your agent halts safely instead of hallucinating data.

Cross-agent data pipelines

Isolate your data fetching logic. You can build one agent dedicated solely to querying Brazilian government stats using `list_organizations` and `list_groups`. Once it finds the right publisher, it hands the metadata off to an analysis agent. That separation keeps your context windows clean. The researcher agent uses `list_packages` to map the available datasets, while a secondary agent downloads the actual files via `get_package` and parses the Portuguese text.

Auto-discover 8 agricultural tools

Pass the server to your Agent constructor and you're done. The SDK automatically reads the MCP specification and registers tools like `get_organization` and `list_tags` without manual mapping. Set `cacheToolsList=True` to eliminate startup latency. Your agent starts instantly, already knowing how to query MAPA records and pull official Brazilian crop statistics on demand.

Setup guide

Set up MAPA (Agricultura) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all MAPA (Agricultura) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives MAPA (Agricultura) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MAPA (Agricultura) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="MAPA (Agricultura) Agent",
            instructions="You have access to MAPA (Agricultura) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 MAPA (Agricultura). 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 MAPA (Agricultura) 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 MAPA (Agricultura) MCP in OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance pointing to the Vinkius MCP Server endpoint. Pass it to your agent's `mcp_servers` array.

Yes. Set `cacheToolsList=True` when initializing the server connection. This stops the agent from reloading the 8 tool definitions every time it boots.

The agent automatically discovers `search_packages`. You can pass queries like "agrofit" or "organization:mapa" directly through your conversational prompts.

Implement retry logic in your agent's guardrails. If a `get_resource` call fails due to throttling, the SDK can catch the error and queue a delayed retry.

You're pulling public Brazilian agricultural open data, so inbound data is not sensitive. However, your outbound search queries to `search_packages` pass through the Vinkius zero-trust sandbox. The server runs ephemerally, meaning no query logs or API tokens persist after your agent disconnects.

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