How to Use the Idealista (Real Estate) MCP in LangChain

Q: What happens if my agent searches for commercial spaces without specifying the transaction type?

The localescomerciales tool defaults to rental properties if your agent does not define a purchase parameter. Your chain should explicitly instruct the agent to set this parameter if you only want purchase listings.

Feed real-time Spanish, Italian, and Portuguese property data straight 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 Idealista (Real Estate) MCP to LangChain

Create your Vinkius account to connect Idealista (Real Estate) 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 Idealista (Real Estate) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pinpoint listings by coordinate chains

The `buscar_inmuebles` tool queries the Idealista database using precise GPS coordinates and search radii. Your LangChain agent runs this tool to pull raw property data, then feeds those exact coordinates directly into subsequent chain links to map local amenities or calculate commute times. Look, you get clean, unformatted JSON containing prices and square footage without scraping. Use `pisos_venta` in the same sequence to isolate properties for sale in specific neighborhoods, letting your chain filter out overpriced listings before they reach your database.

Chain commercial and rental MCP Server searches

The `locales_comerciales` tool pulls active commercial listings, defaulting to rentals unless your agent explicitly requests purchase options. LangChain chains this output with `pisos_alquiler` using our MCP connection to help your agent compare commercial rent trends against residential rates in the same postal code. This multi-tool pipeline runs inside a single LangGraph run, sending the output of your commercial search directly into your financial modeling chains. You track every API call, latency spike, and token count inside LangSmith without writing custom logging wrapper code.

Track Iberian construction projects

The `obra_nueva` tool exposes newly built residential projects and off-plan developments across Spain, Italy, and Portugal. Your agent triggers this tool to scan for fresh inventory, then passes the results to a separate chain that checks builder reputations or local permit registries. This setup bypasses manual portal searches entirely. Your LangChain pipeline receives structured data on construction status and unit availability, letting you build automated alerts that ping your team the second a new development hits the market.

Setup guide

Set up Idealista (Real Estate) 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 Idealista (Real Estate) 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({
    "idealista-real-estate-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 Idealista (Real Estate) 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 Idealista. 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 Idealista (Real Estate) 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 Idealista (Real Estate) MCP in LangChain

Use the MultiServerMCPClient to load the tools into your agent's toolkit. Your agent calls `buscar_inmuebles` to find raw listings, then passes those results to a second chain step for filtering.

You must handle rate limiting at the chain level or within your LangGraph configuration. The MCP server passes raw API responses directly, so your chain needs to back off when it hits provider limits.

Connect your agent to LangSmith to monitor every execution of `pisos_venta` or `pisos_alquiler`. You will see the exact inputs, outputs, and execution times for every property search.

The `locales_comerciales` tool defaults to rental properties if your agent does not define a purchase parameter. Your chain should explicitly instruct the agent to set this parameter if you only want purchase listings.

Your search parameters, GPS coordinates, and budget filters run inside an isolated V8 sandbox on Vinkius. No query data or location coordinates are stored or shared outside the temporary execution context.

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