Property Comps MCP Server

An MCP (Model Context Protocol) server that gives AI agents access to comparable sales data and property transactions across 16 markets in 6

Local serverstdioPython

What is the Property Comps MCP server?

Most developer tooling work still happens through a UI a human drives. Property Comps MCP server moves it into the conversation instead. An MCP (Model Context Protocol) server that gives AI agents access to comparable sales data and property transactions across 16 markets in 6 countries. 43M+ records sourced from government open data registries -- not estimates, not.

The short version

  • "What are comparable sales near 10001 in NYC?"
  • "What's the median property price in Dubai Marina?"
  • "Show me recent sales near SW1A1DA in London"
  • "Compare Seattle vs Phoenix house prices"
  • "What sold near 80202 in Denver last 6 months?"

The tools it exposes

The server publishes 3 tools. What each one is for:

  • search_property_comps — Search comparable sales by location and radius. Returns prices, dates, addresses, property types, and statistics
  • get_area_stats — Get area price statistics: median, average, min, max, broken down by property type
  • list_markets — List all 16 available markets with transaction counts and examples

Getting it running

Installation goes through your MCP client rather than a global install: point it at mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Property Comps's toolset — search_property_comps, get_area_stats, list_markets — is a fair guide to whether it matches your workflow. It is maintained by tianning-lab; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Property Comps's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
search_property_compsSearch comparable sales by location and radius. Returns prices, dates, addresses, property types, and statistics.
get_area_statsGet area price statistics: median, average, min, max, broken down by property type.
list_marketsList all 16 available markets with transaction counts and examples.

How to install the Property Comps MCP server

{
  "mcpServers": {
    "property-comps": {
      "command": "uvx",
      "args": ["mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Property Comps to search property comps.
  • Use Property Comps to get area stats.
  • Use Property Comps to list markets.

Frequently asked questions

It connects Property Comps to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (search_property_comps, get_area_stats, list_markets) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Property Comps directly.