Memory MCP Server
Persistent memory using a knowledge graph
Commercial real estate deal search, comp lookup, and scoring for the Northeast US
{
"mcpServers": {
"io-github-creintel-ndi-mcp-server": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Commercial real estate deal search, comp lookup, and scoring for the Northeast US
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Commit history unknown.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationNo known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Hash-verified file editing MCP server with token efficiency hook. 11 tools for AI coding agents.
MCP Security Weekly
Get CVE alerts and security updates for io.github.CREIntel/ndi-mcp-server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Connect any MCP-compatible LLM (Claude, Cursor, Continue) to 14,000+ AI-scored commercial real estate deals and 100,000+ closed comps across the Northeast.
Ask your LLM natural language questions like:
| Tool | Description | Tier Required |
|---|---|---|
search_deals | Find active listings by state, type, score, price, cap rate | Any |
get_deal | Full deal details + scoring breakdown + sell signal | Any |
search_comps | 100K+ closed transactions for benchmarking | agent_starter |
score_deal | Submit any deal for AI scoring | agent_pro |
get_market_benchmarks | Cap rate + PSF benchmarks by state/type | Any |
find_1031_candidates | Filtered search for exchange-ready deals | Any |
get_sell_signal | Sell probability for a specific listing | agent_starter |
get_market_summary | State-level market overview | Any |
Sign up at northeastdealintel.com/agent-api.html
search_deals, get_deal, search_comps, get_sell_signal, get_market_summaryscore_deal (submit any deal for AI scoring)pip install mcp httpx
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or
%APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"northeast-deal-intel": {
"command": "python3",
"args": ["/path/to/ndi_mcp_server.py"],
"env": {
"NDI_API_KEY": "your_api_key_here"
}
}
}
}
Restart Claude Desktop. You'll see the NDI tools available in the tool picker.
The server uses stdio transport (standard). Any MCP-compatible client works the same way — just point it at ndi_mcp_server.py with NDI_API_KEY in the environment.
Cursor: Add to .cursor/mcp.json in your project root.
Continue: Add to ~/.continue/config.json under mcpServers.
1031 Exchange
"I sold a CT strip center for $1.8M and need a replacement property within 45 days. Find me NNN retail with cap rates above 7% priced between $1.5M and $2.2M."
Market Research
"What's the average cap rate for industrial in Hartford vs. Fairfield County right now? Show me the top 5 deals in each submarket."
Deal Underwriting
"Score this deal: 45 Industrial Dr, Wallingford CT. Asking $4.1M, 47,000 SF warehouse, single tenant NNN, 6.8% cap, 4 years remaining on lease."
Distress Hunting
"Find me deals in CT with high sell probability — I'm looking for motivated sellers. Focus on industrial and multifamily."
https://api.northeastdealintel.com
Override with env var: NDI_API_BASE=https://api.northeastdealintel.com