How to Use the Comunidad de Madrid (Portal Regional) MCP in AutoGen

Q: How do AutoGen agents handle large datasets returned from Comunidad de Madrid (Portal Regional)?

Your agents can use searchdatastore to request paginated chunks. A critic agent can then monitor token usage and instruct the query agent to stop fetching once it has enough Madrid data.

Let your AutoGen agents debate and analyze public data from Comunidad de Madrid (Portal Regional).

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comunidad de Madrid (Portal Regional) MCP to AutoGen

Create your Vinkius account to connect Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus on Madrid datasets.

`search_datasets` allows one AutoGen agent to find public Madrid records matching a topic, while a second agent reviews the results. They debate whether the returned Madrid datasets actually contain the necessary regional information using this MCP server tool. This collaborative filtering ensures your AutoGen system doesn't waste tokens processing irrelevant resources. The agents agree on the best Madrid dataset ID before executing further queries.

Run an AutoGen agent debate over Madrid datastore records.

`search_datastore` extracts raw data rows that your AutoGen analyst agent inspects. Meanwhile, a critic agent challenges the data's relevance or completeness based on the Madrid schema details. They negotiate the final output, ensuring that the synthesized AutoGen report on Madrid's public metrics is accurate. You get a polished, double-checked summary of Madrid's records instead of a raw dump.

Automated resource verification.

`get_resource` retrieves metadata for specific files, which your AutoGen coordinator agent distributes to specialized worker agents. One worker checks the Madrid file size, while another validates the update frequency. They vote on whether to proceed with downloading the resource from the Madrid portal. This prevents your AutoGen system from getting stuck on corrupt or outdated files from the regional portal.

Setup guide

Set up Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) 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="Comunidad de Madrid (Portal Regional)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Comunidad de Madrid (Portal Regional) 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="Comunidad de Madrid (Portal Regional)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional). 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 Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) MCP in AutoGen

You register the tools with an AssistantAgent. One agent can call `list_datasets` to find Madrid IDs, then pass those IDs in a message to a researcher agent who calls `get_dataset`.

Yes, you define which agents receive the tools list in their constructor. This lets you isolate Madrid data access to a single researcher agent while keeping your writer agent clean.

Your agents can use `search_datastore` to request paginated chunks. A critic agent can then monitor token usage and instruct the query agent to stop fetching once it has enough Madrid data.

It uses Streamable HTTP transport configured through Vinkius. The `autogen-ext` package maps these HTTP endpoints to local schemas seamlessly.

Vinkius manages the MCP server authentication layer using a single endpoint token. Your AutoGen code never handles raw Madrid portal keys, and the connection runs inside a secure, sandboxed environment.

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