DealFlowPro MCP Server — Analyze multifamily real estate deals from Claude Code or Claude Desktop
DealFlowPro MCP Server
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Analyze multifamily real estate deals from Claude Code, Cursor, Claude Desktop, or any MCP-compatible client.
DealFlowPro is an AI-powered multifamily deal analysis platform. This MCP server wraps the DealFlowPro REST API, giving AI agents access to institutional-grade underwriting calculations.
Demo
What You Can Do
Ask Claude naturally and it calls the right tool:
- "Analyze this 24-unit deal in Charlotte — asking $2M, $13.6K/mo rent, $5.5K expenses"
- "Score this deal: 12 units, $1.5M, $9K monthly income"
- "What's the max I should offer on a property with $28.8K/mo rent if I want 8% cash-on-cash?"
- "Is this property in a flood zone? 2909 Burgess Dr, Charlotte, NC"
Tools
| Tool | Description |
|------|-------------|
| analyze_deal | Full deal analysis: cap rate, DSCR, cash-on-cash, IRR, DFP Score (0-100), max offer price, yearly cashflows |
| score_deal | Quick screening: DFP Score + key metrics |
| reverse_calc | Max offer price from target returns (cap rate, CoC, DSCR, IRR) |
| market_data | Flood zone, neighborhood income vs state median, job growth for any address |
All four carry MCP 2025-06-18 annotations (title, readOnlyHint, destructiveHint, idempotentHint, openWorldHint). Every tool is read-only.
Install as a Claude plugin
This repo doubles as a Claude Code / Cowork plugin. The plugin connects to the
remote server at https://dealflowpro.io/mcp rather than the npm package above,
which means:
- **Eight tools instead of four.** Adds list_my_deals, get_deal_analysis,
get_my_criteria, and portfolio_summary — your saved deals, buy-box
criteria, and pipeline, scoped to your account.
- **OAuth instead of an API key.** No DFP_API_KEY to export; you sign in to
your DealFlowPro account when the plugin connects.
Use the npm package below instead if you want a local stdio server, prefer API
key auth, or are wiring DealFlowPro into a non-Claude MCP client.
For Institutional AI Teams
DealFlowPro is built to slot into AI eval pipelines and production AI stacks. The MCP server (this package, plus the remote endpoint at https://dealflowpro.io/mcp) wraps the same engine as the REST API — schema-strict, idempotent, predictable.
**Auth + scoping.** Every tool call is authenticated, with a Bearer API key or, on the remote endpoint, an OAuth sign-in. Calls are scoped to the account that issued the key or signed in — no cross-tenant access path. Per-tool audit lines land in your account's logs/mcp_tool_calls.log capturing tool name + flattened arg keys (not values) — usage is auditable without exposing deal contents.
**Rate limits per tier.**
| Tier | Daily limit | Monthly | Cost |
|------|------------:|--------:|-----:|
| Free | 5 requests, lifetime | — | free, no card |
| Pay-as-you-go | balance-based | per credits | $1/request |
| Essentials | 50 req/day | ~1,500 | $79/mo |
| Premium | 200 req/day | ~6,000 | $149/mo |
| Enterprise | 1,000 req/day | ~30,000 | $399/mo |
Rate limit headers (X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset) returned on every response. 429 responses include Retry-After.
**Error codes.** Stable, documented at dealflowpro.io/api/docs/#errors — all errors are JSON {success: false, error: {code, message}} shape. Codes: invalid_input (400), invalid_json (400), unauthorized (401), tier_required (403), method_not_allowed (405), payload_too_large (413), rate_limit_exceeded (429), internal_error (500).