How to Use the Dades Obertes Catalunya MCP in AutoGen

Q: How do I add Dades Obertes Catalunya to my AutoGen setup?

Use mcpservertools with your Vinkius HTTP endpoint. Pass the resulting tool list into your AssistantAgent constructor to let them access the public catalog.

Q: Can AutoGen agents fix broken SoQL queries for Dades Obertes Catalunya?

Yes. If the query tool returns an error regarding a bad $limit parameter, the agents read the error message, discuss the syntax mistake, and retry.

Let AutoGen agents debate and analyze public Catalonia data by querying datasets via this MCP integration to form consensus on regional trends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dades Obertes Catalunya MCP to AutoGen

Create your Vinkius account to connect Dades Obertes Catalunya 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 Dades Obertes Catalunya with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Data Discovery

Finding the right public record requires iteration. A research agent triggers `search_catalog` to find potential government datasets matching your topic. A secondary critique agent reviews those search results. They discuss which alphanumeric ID actually represents the most accurate source before moving forward.

Query with this MCP Server

Once your agents agree on a source, they need to extract the rows. The execution agent calls `query_dataset` using specific SoQL parameters to pull the exact metrics. If the query fails or returns too much data, the agents notice. They negotiate a tighter `$where` clause and run the extraction again until the output fits their needs.

Form Consensus on Civic Data

Raw government statistics often require interpretation. One agent analyzes the retrieved municipal data for positive trends, while a skeptic agent looks for anomalies. They argue over the fetched numbers until they reach a logical conclusion. You get a final report based on actual public records rather than a single LLM's blind guess.

Setup guide

Set up Dades Obertes Catalunya 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 Dades Obertes Catalunya 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="Dades Obertes Catalunya_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Dades Obertes Catalunya 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="Dades Obertes Catalunya_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Dades Obertes Catalunya 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 Dades Obertes Catalunya. 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 Dades Obertes Catalunya 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 Dades Obertes Catalunya MCP in AutoGen

Use `mcp_server_tools` with your Vinkius HTTP endpoint. Pass the resulting tool list into your `AssistantAgent` constructor to let them access the public catalog.

Yes. If the query tool returns an error regarding a bad `$limit` parameter, the agents read the error message, discuss the syntax mistake, and retry.

Complex data analysis requires multiple perspectives. A single script just pulls rows, whereas a multi-agent system actively debates what those rows mean for your specific research question.

They figure it out themselves. The MCP framework handles the schema conversion automatically, so the agents know they must run the search tool before the query tool.

This server strictly interacts with open regional statistics like population counts. Vinkius manages the authentication invisibly and tears down the ephemeral environment the second your agents finish their conversation.

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