How to Use the Junta de Andalucía (Portal) MCP in LangChain

Q: How do I connect the Junta de Andalucía (Portal) MCP server to LangChain?

Install langchain-mcp-adapters. Initialize a MultiServerMCPClient with the server URL and pass the output of client.gettools() to your agent.

Q: Can LangChain agents automatically search Junta de Andalucía (Portal) datasets?

Yes. The agent uses the searchdatastore tool to run queries against specific resources. It evaluates the results and decides if it needs to adjust the search parameters.

Q: Does the integration support session tracking?

The client is stateless by default. You must use client.session() to maintain context across multiple API calls to the Andalusian portal.

Build composable data pipelines with LangChain that pull public records directly from the Andalusian government.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Junta de Andalucía (Portal) MCP to LangChain

Create your Vinkius account to connect Junta de Andalucía (Portal) 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 Junta de Andalucía (Portal) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Andalusian Data Tools

The `list_packages` tool feeds raw dataset names directly into your LangChain agent's context window. From there, your ReAct agent decides which specific datasets warrant a deeper look. It triggers `get_package` to pull the exact metadata needed for the next step in the sequence. You track every single API call through LangSmith. If a query stalls, you see exactly where the chain broke down and how many tokens it burned. The agent handles the pagination and routing without you writing custom parsing logic.

Query the Datastore via MCP Server

Calling `search_datastore` lets your pipeline extract specific rows from Andalusian public files. You don't have to download massive CSVs locally. The agent passes search parameters through the MCP Server, filtering the records before they ever reach your application. This setup shines when you combine it with external databases. Your chain can pull employment statistics from the portal, format them, and insert them straight into your own PostgreSQL instance. It turns static government data into a live feed.

Navigate Publishing Organizations

Running `list_organizations` returns the exact directory of departments publishing data to the Junta. Your LangGraph setup can map these entities and automatically monitor specific departments for new releases. If the health department drops a new file, your agent knows immediately. You then pass the organization ID to `list_groups` to categorize the findings. The agent builds a structured map of the government's data hierarchy. Everything happens in memory, step by step, driven by intermediate results.

Setup guide

Set up Junta de Andalucía (Portal) 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 Junta de Andalucía (Portal) 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({
    "junta-de-andalucia-portal-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 Junta de Andalucía (Portal) 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 Junta de Andalucía. 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 Junta de Andalucía (Portal) 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 Junta de Andalucía (Portal) MCP in LangChain

Install `langchain-mcp-adapters`. Initialize a `MultiServerMCPClient` with the server URL and pass the output of `client.get_tools()` to your agent.

Yes. The agent uses the `search_datastore` tool to run queries against specific resources. It evaluates the results and decides if it needs to adjust the search parameters.

Complex public data requests often require multiple steps. LangGraph lets you build a stateful workflow that calls `get_package` and then `get_resource` in a specific, reliable order.

The client is stateless by default. You must use `client.session()` to maintain context across multiple API calls to the Andalusian portal.

This server only reads public government datasets and open metadata. It uses a zero-trust, ephemeral connection that forgets your queries 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