JL

johnstenner/loopnetmcp

Developer tools

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

15 stars 6 forks Качество 63 Тренд 21MIT

MCP server for searching Loopnet commercial real estate listings with Akamai bypass

Обзор

An MCP (Model Context Protocol) server that provides Claude Code with real-time access to commercial real estate data from Loopnet, the largest CRE marketplace in the US. Loopnet has no public API — this server scrapes the site and exposes structured data through three tools that any Claude Code session can call via natural language. Once registered with Claude Code, you can ask things like: - "Find office buildings for sale in Houston, TX under $5M" - "Get details on this Loopnet listing: https://www.loopnet.com/Listing/..." - "Give me a market overview for retail properties in Miami, FL" The server fetches live data from Loopnet, parses the HTML, and returns structured results — property names, addresses, prices, sizes, cap rates, broker info, images, and more. office, retail, industrial, multifamily, land, hospitality, special-purpose, health-care - City and state: "Houston, TX", "New York, NY" - State abbreviation: "TX" - Zip code: "77001" - Python 3.

README

Показан фрагмент оригинального README. Открыть оригинал.

Loopnet MCP Server

An MCP (Model Context Protocol) server that provides Claude Code with real-time access to commercial real estate data from Loopnet, the largest CRE marketplace in the US. Loopnet has no public API — this server scrapes the site and exposes structured data through three tools that any Claude Code session can call via natural language.

What It Does

Once registered with Claude Code, you can ask things like:

  • “Find office buildings for sale in Houston, TX under $5M”
  • “Get details on this Loopnet listing: https://www.loopnet.com/Listing/…”
  • “Give me a market overview for retail properties in Miami, FL”

The server fetches live data from Loopnet, parses the HTML, and returns structured results — property names, addresses, prices, sizes, cap rates, broker info, images, and more.

Tools

Tool Description Key Parameters
search_properties Search for CRE listings by location and filters location, property_type, listing_type, price_min/max, size_min/max
get_property_details Get full details on a specific listing url_or_id (Loopnet URL or listing ID)
get_market_overview Aggregate market statistics for an area location, property_type

Supported Property Types

office, retail, industrial, multifamily, land, hospitality, special-purpose, health-care

Supported Listing Types

for-sale, for-lease

Location Formats

  • City and state: "Houston, TX", "New York, NY"
  • State abbreviation: "TX"
  • Zip code: "77001"

Setup

Prerequisites

Installation

git clone  && cd LoopnetMCP

# Create virtual environment and install
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

Register with Claude Code

claude mcp add \
  --scope user \
  --transport stdio \
  loopnet \
  -- python3 /path/to/LoopnetMCP/src/loopnet_mcp/server.py

Use --scope user to make the server available in all Claude Code sessions, or --scope project to restrict it to a single project directory.

After registration, restart Claude Code. Verify with /mcp — the loopnet server should appear as connected with 3 tools.

Configuration

All settings are optional and have sensible defaults. Override via environment variables or a .env file (see .env.example):

Variable Default Description
LOOPNET_REQUEST_DELAY_SECONDS 3.0 Minimum delay between HTTP requests
LOOPNET_MAX_CONCURRENT_REQUESTS 1 Max concurrent HTTP requests
LOOPNET_TIMEOUT_SECONDS 30.0 HTTP request timeout
LOOPNET_MAX_RETRIES 3 Retry count for failed requests
LOOPNET_CACHE_TTL_SECONDS 300 Cache TTL (5 minutes)
LOOPNET_CACHE_MAX_ENTRIES 500 Maximum cached responses
Открыть полный README на GitHub

Установка

This server does not publish a one-line install command.

Open the repository installation guide Новичок в MCP? Начните с руководства на mcpskill.org →