Skip to main content

AI-powered commercial real estate deal search, comp lookup, and property scoring for the Northeast US via MCP

Project description

NDI MCP Server

AI-powered commercial real estate intelligence for the Northeast US — via the Model Context Protocol.

Use this server to give Claude, Cursor, Windsurf, or any MCP client direct access to:

  • 14,000+ AI-scored active listings across CT, MA, NJ, NY, PA, RI, NH, VT, ME
  • 100,000+ closed sale comps with price/SF and cap rate benchmarks
  • Institutional-grade deal scoring — 4-lens framework used by professional investors
  • Sell probability signals — predict which sellers are motivated to transact
  • 1031 exchange matching — find qualified replacement properties by criteria

Built by Northeast Deal Intel.


Quick Start

Install

pip install ndi-mcp-server

Get an API Key

Sign up at northeastdealintel.com/agent-api.html.
Agent Starter tier ($49/mo) unlocks all 8 tools.

Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "northeast-deal-intel": {
      "command": "ndi-mcp-server",
      "env": {
        "NDI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Configure Cursor / Windsurf

Add to .cursor/mcp.json or .windsurf/mcp.json:

{
  "mcpServers": {
    "northeast-deal-intel": {
      "command": "ndi-mcp-server",
      "env": {
        "NDI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Available Tools

Tool Description Tier Required
search_deals Search active listings by state, type, score, price, cap rate Free
get_deal Full deal detail with AI scoring breakdown + sell signal Free
get_market_benchmarks Cap rate & price/SF benchmarks from closed comps Free
get_market_summary Active listings, score distribution, top submarkets Free
find_1031_candidates Find 1031-qualified replacement properties Free
search_comps Search 100K+ closed transactions Agent Starter ($49/mo)
get_sell_signal Sell probability for any listed property Agent Starter ($49/mo)
score_deal Submit any deal for AI scoring (not in our DB) Agent Pro ($149/mo)

Example Prompts

Once connected, try asking Claude or Cursor:

  • "Find industrial deals in Connecticut scoring above 7.5 with cap rates over 7%"
  • "Pull comps for multifamily sales in Hartford County in the last 12 months"
  • "I have $2.5M in a 1031 exchange — find qualified replacement properties in the Northeast"
  • "Score this deal: 5,000 SF retail in Stamford CT asking $1.2M at 6.8% cap"
  • "Which CT industrial listings show the highest sell probability right now?"

API Tiers

Tier Price Tools
Free $0 search_deals, get_deal, benchmarks, summary, 1031 matching
Agent Starter $49/mo + search_comps, get_sell_signal, owner lookup
Agent Pro $149/mo + score_deal (score any property), full comp access

Get your API key →


License

MIT — see LICENSE

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ndi_mcp_server-1.0.1.tar.gz (7.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ndi_mcp_server-1.0.1-py3-none-any.whl (9.5 kB view details)

Uploaded Python 3

File details

Details for the file ndi_mcp_server-1.0.1.tar.gz.

File metadata

  • Download URL: ndi_mcp_server-1.0.1.tar.gz
  • Upload date:
  • Size: 7.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for ndi_mcp_server-1.0.1.tar.gz
Algorithm Hash digest
SHA256 cc35f92b4a8c757f96f1e1b2bb8f720b4d8d91004d54686ca5b30d0ab8e6c0a5
MD5 57eeb1e8bbe6f4688c0e88da3d61bafe
BLAKE2b-256 be3759dfe8a5bec39eaa55f6ac529a400692f1f4deb4f4879b049cf50791532f

See more details on using hashes here.

File details

Details for the file ndi_mcp_server-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: ndi_mcp_server-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 9.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for ndi_mcp_server-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ed704f1ed24701aedb7b19eee9714ca0925a02354283b778bbc626ab46294863
MD5 c6e0a4cb4a407b276be1d5d076ab9917
BLAKE2b-256 18421756ed80cd8a645170afeb85b249a7a27b237a6ff4946b2b9398d66e5d10

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page