How to Use the IBESTAT (Estadística Illes Balears) MCP in LangChain

Q: Can I use multiple MCP tools in a single chain?

You should use listresources first to locate specific sub-tables. This keeps the payload size manageable for your agent's context window and prevents token overflow during large queries.

Feed clean Balearic statistical data directly into your LangChain multi-step reasoning chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBESTAT (Estadística Illes Balears) MCP to LangChain

Create your Vinkius account to connect IBESTAT (Estadística Illes Balears) 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 IBESTAT (Estadística Illes Balears) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Balearic data sources with LangChain

The `list_operations` tool lets your agent discover the exact statistical datasets available in the IBESTAT database. It returns unique identifiers that you can pass directly to down-chain processing nodes without manual copy-pasting. LangChain handles this by feeding these identifiers to subsequent steps in a ReAct loop. You get full visibility over the token usage and latency of each call through LangSmith tracing, making it easy to debug complex multi-step data pipelines.

Pull raw dataset tables on demand

The `get_data` tool extracts the actual numeric tables and statistical values for a given resource ID. Your agent reads the raw numbers, formats them, and feeds them directly into your database or analysis files. Since the output is structured, you can link this tool to LangChain data parsers. This lets you build pipelines that fetch regional tourism numbers or employment metrics and immediately run them through custom mathematical calculations.

Inspect statistical metadata automatically

The `get_metadata` tool pulls the structural definitions, units, and classifications for any statistical operation. This ensures your agent doesn't hallucinate the meaning of specific data columns or metrics. By combining this with an MCP Server, your chains verify the data structure before trying to process it. The agent checks the rules, validates the schema, and only runs the main data query when the parameters match the expected format.

Setup guide

Set up IBESTAT (Estadística Illes Balears) 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 IBESTAT (Estadística Illes Balears) 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({
    "ibestat-estadistica-illes-balears-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 IBESTAT (Estadística Illes Balears) 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 IBESTAT. 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 IBESTAT (Estadística Illes Balears) 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 IBESTAT (Estadística Illes Balears) MCP in LangChain

You use the MultiServerMCPClient adapter to register the server endpoint. Once connected, call the get_tools method to expose the statistical tools directly to your agent. From there, the agent invokes the tools during its reasoning loops.

Yes, every tool execution shows up in LangSmith automatically. You can monitor the exact inputs sent to `get_data` and see the raw JSON payload returned by the Balearic statistical registry. This makes latency debugging straightforward.

LangChain allows you to configure standard LLM caching or custom tool-level caches. This is useful for `get_metadata` queries to avoid hitting the regional API repeatedly for static schemas.

You should use `list_resources` first to locate specific sub-tables. This keeps the payload size manageable for your agent's context window and prevents token overflow during large queries.

This MCP Server runs in a zero-trust, ephemeral V8 isolate on Vinkius. It only handles public statistical tables and operation metadata, meaning no private user data is ever stored or exposed to external networks.

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