Booli

You run a Booli MCP Server to query Swedish real estate data from Booli.se through a GraphQL endpoint. It enables natural language questions to search for properties, discover locations, and obtain structured results that AI agents can interpret and present.

How to use

You connect your MCC client to the Booli MCP Server using either the remote HTTP endpoint or the local, node-based server. The HTTP option talks directly to Booli’s GraphQL API, while the local server runs on your machine and exposes the same functionality through an in-process command you start.

How to install

Prerequisites: you need Node.js installed on your machine.

Install dependencies and build the server.

npm install
npm run build

Configuration and usage notes

Environment variable to configure the GraphQL endpoint is BOOLI_GRAPHQL_URL.

Development run and production start are available for the local server.

# Development server
npm run dev

# Production server
npm start

With Claude Desktop MCP configuration

You can add a local Booli MCP Server to Claude Desktop using a JSON configuration that runs the server with Node.js and points to the GraphQL endpoint.

{
  "mcpServers": {
    "booli": {
      "command": "node",
      "args": ["/path/to/booli-mcp-server/dist/index.js"],
      "env": {
        "BOOLI_GRAPHQL_URL": "https://api.booli.se/graphql"
      }
    }
  }
}

Available tools

search_locations

Find location suggestions and area IDs for property searches. This tool accepts a query string and optional limit to return matching locations or area IDs.

search_properties

Perform property searches with comprehensive filters such as location, price, rooms, area, and advanced criteria like price per square meter, construction year, and amenities.