How to Use the Dades Obertes Catalunya MCP in LangChain

Q: How do I connect Dades Obertes Catalunya to LangChain?

Install langchain-mcp-adapters. Then initialize a MultiServerMCPClient pointing to the Vinkius endpoint and pass the extracted tools into your agent constructor.

Q: Can LangChain agents write their own SoQL queries for Dades Obertes Catalunya?

Yes. The agent figures out the $where and $limit parameters based on your prompt. It calls the query tool with those exact filters to avoid pulling unnecessary rows.

Build ReAct agents in LangChain that query Catalonia's public datasets via this MCP server and chain the results into your analytical pipelines.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Catalogs with this MCP Server

Your ReAct agent needs an exact dataset ID before it pulls records. It hits `search_catalog` to scan the Catalonia Open Data portal for keywords like 'transit' or 'budget'. The tool returns the specific alphanumeric identifier required for the next step. You pipe that ID straight into your next LangChain node without human intervention.

Execute SoQL Queries

Pulling raw dumps wastes tokens. Your agent uses `query_dataset` to apply precise SoQL filters like `$select`, `$where`, and `$limit` right at the source. LangSmith traces every parameter your chain generates. You see exactly how the agent narrowed down a million-row demographic table to just three relevant records.

Chain Open Data Outputs

Public data rarely exists in a vacuum. You take the JSON output from a Catalonia dataset query and feed it immediately into a vector store or a separate SQL database tool. The output of one tool call strictly drives the input of the next. Your multi-step reasoning pipeline handles the entire extraction and formatting process automatically.

Setup guide

Set up Dades Obertes Catalunya 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 Dades Obertes Catalunya 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({
    "dades-obertes-catalunya-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 Dades Obertes Catalunya 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 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 LangChain

Install `langchain-mcp-adapters`. Then initialize a `MultiServerMCPClient` pointing to the Vinkius endpoint and pass the extracted tools into your agent constructor.

Yes. The agent figures out the `$where` and `$limit` parameters based on your prompt. It calls the query tool with those exact filters to avoid pulling unnecessary rows.

Every call to the catalog search logs the exact inputs and latency. You track exactly how many tokens your agent spent digging through public records.

It runs the search tool first. The ReAct loop analyzes the search results, extracts the correct ID, and then triggers the query tool in the next iteration.

This integration only reads public municipal and regional records from Catalonia. Vinkius isolates the connection in an ephemeral V8 sandbox, meaning your chain's query parameters vanish the moment the session ends.

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