How to Use the Maranhão Open Data MCP in AutoGen

Q: How do AutoGen agents collaborate on Maranhão Open Data?

One AutoGen agent can use searchpackages to find a dataset, while a second agent uses getpackage to inspect it. They discuss the metadata in their chat history to decide if the data is relevant.

Q: Can I use SQL tools with Maranhão Open Data in AutoGen?

Yes, you can register searchdatastoresql as an MCP tool for your AutoGen AssistantAgent. The coder agent writes the SQL, executes it, and shares the tabular output with the rest of the agent group.

Q: How do AutoGen agents handle bad data from Maranhão Open Data?

If searchdatastore returns an error or empty results, your AutoGen critic agent can suggest a different query or instruct the search agent to use listpackages to find a different dataset.

Deploy AutoGen multi-agent teams to debate, verify, and analyze Maranhão Open Data public records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maranhão Open Data MCP to AutoGen

Create your Vinkius account to connect Maranhão Open Data 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 Maranhão Open Data with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents discover Maranhão Open Data

The `search_packages` tool allows your AutoGen discovery agent to find specific datasets on the Maranhão portal using keyword queries. The agent can search for topics like healthcare or infrastructure and pass the matching package list to its peer agents. A separate analyst agent can then use `get_package` to review the dataset's metadata. This cooperative workflow ensures your agents find and verify the correct data sources before performing any analysis.

Run collaborative SQL queries with this MCP Server

The `search_datastore_sql` tool allows your AutoGen coder agent to write and execute SQL queries directly against the Maranhão datastore. The raw query results are returned to the agent conversation for collaborative review. A critic agent can inspect the returned SQL data, flag anomalies, and ask the coder agent to refine the query using `search_datastore`. This back-and-forth debate ensures your team produces highly accurate reports on Brazilian state spending using this MCP Server.

Verify Maranhão resource schemas in AutoGen

The `get_resource` tool lets your AutoGen agents inspect the specific details of a data resource, such as a CSV file's structure or an API endpoint. This allows a data-engineer agent to verify the schema before any queries are run. If the schema doesn't match expectations, the agent can use `list_packages` to find alternative datasets. This automated quality check prevents your analysis agents from running failing queries on mismatched data structures.

Setup guide

Set up Maranhão Open Data 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 Maranhão Open Data 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="Maranhão Open Data_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Maranhão Open Data 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="Maranhão Open Data_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Maranhão Open Data 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 Maranhão Open Data. 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 Maranhão Open Data 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 Maranhão Open Data MCP in AutoGen

One AutoGen agent can use `search_packages` to find a dataset, while a second agent uses `get_package` to inspect it. They discuss the metadata in their chat history to decide if the data is relevant.

Yes, you can register `search_datastore_sql` as an MCP tool for your AutoGen AssistantAgent. The coder agent writes the SQL, executes it, and shares the tabular output with the rest of the agent group.

If `search_datastore` returns an error or empty results, your AutoGen critic agent can suggest a different query or instruct the search agent to use `list_packages` to find a different dataset.

AutoGen connects using the Streamable HTTP transport provided by the Vinkius platform. This allows your multi-agent system to call the Maranhão tools securely without running local server instances.

Your SQL queries and retrieved Brazilian public records are processed in an ephemeral V8 sandbox. Vinkius manages the token authentication, ensuring that your AutoGen agents query the state database securely without saving data.

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