How to Use the Gipuzkoa Irekia MCP in LangChain

Q: Can I trace Gipuzkoa Irekia tool calls in LangChain using LangSmith?

Yes, every execution of tools like searchpackages shows up in your LangSmith dashboard automatically. Monitoring latency, input parameters, and exact payloads returned from the Basque open data API becomes straightforward.

Q: What is the best way to handle multi-step data fetching with Gipuzkoa Irekia in LangChain?

Use a ReAct agent loop that first queries listorganizations to identify the data owner. After that, the agent chains that output into showorganization to locate the exact datasets you need.

Feed real-time Basque regional data directly into your LangChain chains and ReAct agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gipuzkoa Irekia MCP to LangChain

Create your Vinkius account to connect Gipuzkoa Irekia 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 Gipuzkoa Irekia with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Basque public data structures in active chains

Your LangChain agent uses `list_groups` to discover thematic datasets and routes the output to the next step of your chain. This tool maps out public data categories like environment or budget before you execute a query. LangSmith traces every step of this process, tracking token usage and execution latency. You see exactly how your chain transitions from discovering groups to fetching specific files.

Run multi-step searches with the MCP Server

The MCP Server exposes `search_packages` so your LangChain agent can find specific datasets about Gipuzkoa infrastructure. Evaluating the search results, the agent decides which identifier to pass to the next tool in the sequence. Integrating this with your existing vector stores or SQL databases takes only a few lines of code. Your agent acts as an autonomous researcher, pulling raw Basque metadata directly into your application context.

Retrieve raw resource metadata on demand

Accessing specific files requires your LangChain chain to call `show_resource` to grab the target URL. The agent parses the returned payload to extract CSV or JSON links for immediate processing. Because the MCP adapter handles the connection state, your pipelines remain completely stateless. You get clean, structured data payloads without writing custom API wrappers for the regional portal.

Setup guide

Set up Gipuzkoa Irekia 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 Gipuzkoa Irekia 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({
    "gipuzkoa-irekia-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 Gipuzkoa Irekia 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 Gipuzkoa Irekia. 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 Gipuzkoa Irekia 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 Gipuzkoa Irekia MCP in LangChain

Install the MCP adapter package and initialize the client with the server URL. You then fetch the tools using the client and pass them directly to your agent constructor.

Yes, every execution of tools like `search_packages` shows up in your LangSmith dashboard automatically. Monitoring latency, input parameters, and exact payloads returned from the Basque open data API becomes straightforward.

Use a ReAct agent loop that first queries `list_organizations` to identify the data owner. After that, the agent chains that output into `show_organization` to locate the exact datasets you need.

Direct queries go straight to the public API, which operates under standard regional rate limits. If you hit these thresholds, the tools return structured error messages that your agent can read and handle.

Vinkius runs the server in an isolated sandbox, so you don't have to worry about third-party logs. Only public regional metadata and dataset URLs are processed, keeping your local application data secure.

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