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

Q: How do I handle LangChain agent errors when querying Comunidad de Madrid (Portal Regional)?

Catch exceptions directly in your tool execution chain. If getdataset returns a 404, your LangChain agent receives the error string and can fall back to searchdatasets to find the correct Madrid identifier.

Q: Can I trace Comunidad de Madrid (Portal Regional) tool calls with LangSmith in my LangChain app?

Yes, every tool call like searchdatastore is fully traced automatically. You see the exact query parameters sent to the Madrid API and the raw JSON response in your LangSmith console.

Q: How do I pass the Madrid datastore query results to a subsequent LangChain step?

Output from searchdatastore returns as a stringified JSON payload. Your LangChain chain pipes this string directly into the next prompt template, letting the LLM summarize the regional records.

Feed real-time Madrid public datasets directly into your LangChain reasoning loops.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe Madrid open data through LangChain chains.

`list_datasets` acts as the entry point for your LangChain MCP agent to map out available regional information. Your agent inspects the returned identifiers, grabs the right Madrid dataset, and throws it to `get_dataset` to rip out the schema details. This multi-step Madrid data sequence runs inside a single LangChain execution run. You watch the Madrid API inputs and outputs flow through each step on your LangSmith dashboard, verifying exactly how the agent transitions from a broad list to a specific dataset ID.

Query the Madrid datastore dynamically.

`search_datastore` pulls raw records directly from Madrid's regional databases into your active chain. Your LangChain agent uses this tool to extract tabular data, like transit schedules or health metrics, based on the schema it discovered in previous steps. You don't need to hardcode query parameters because your LLM writes them on the fly based on user intent. The output feeds the next prompt in your sequence, allowing your agent to analyze real Madrid numbers without manual data exports.

Filter regional resources in real-time.

`search_datasets` lets your agent find specific public records matching terms like "transporte" or "salud" via the MCP server. The tool returns structured metadata that your LangChain chain parses to find the exact resource ID. Once found, the agent triggers `get_resource` to verify Madrid file formats before downloading. That simple check stops your LangChain pipeline from choking on weird Madrid file types or dead links.

Setup guide

Set up Comunidad de Madrid (Portal Regional) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Comunidad de Madrid (Portal Regional) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "comunidad-de-madrid-portal-regional-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Comunidad de Madrid (Portal Regional) transactions"
    })
    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 LangChain

Catch exceptions directly in your tool execution chain. If `get_dataset` returns a 404, your LangChain agent receives the error string and can fall back to `search_datasets` to find the correct Madrid identifier.

Yes, every tool call like `search_datastore` is fully traced automatically. You see the exact query parameters sent to the Madrid API and the raw JSON response in your LangSmith console.

The agent looks at your prompt's specificity regarding Madrid. If you ask for general topics, it runs `search_datasets` with terms like "transporte", but if you need an index of everything in the Madrid catalog, it defaults to `list_datasets`.

Output from `search_datastore` returns as a stringified JSON payload. Your LangChain chain pipes this string directly into the next prompt template, letting the LLM summarize the regional records.

The MCP server operates inside a secure, ephemeral V8 sandbox. Since the Madrid data is entirely public, no credentials or private regional data are cached or stored on our servers.

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