# refpro-mcp MCP server

Deterministic real estate underwriting, deal analysis & reports: Fix & Flip, BRRRR, construction.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-rickytrinidad-refpro-mcp
- Repository: https://github.com/rickytrinidad/refpro-mcp
- Website: https://refpro.ai

## Install
- Endpoint: https://mcp.refpro.ai/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://mcp.refpro.ai/mcp

## Tools
- deal_quick_check - Run a deterministic, lender-grade quick check on a real-estate deal. Inputs: deal_type (FF | BRRRR | NC), purchase_price, arv_or_value (ARV for FF, refinance value for BRRRR, sellout for NC), rehab_budget, zip_code; optional annual_debt_service, noi_annual, units, units_to_hold. Returns a PASS / MARGINAL / FAIL verdict, the key financial metrics for that deal type (MAO and margin for FF, TPC and DSCR for BRRRR, TPC plus margin or DSCR for NC), and a one-paragraph summary. Math is identical to the underwriting pipeline used in Refpro's full deal pack — no estimates, no rounding shortcuts. Endpoint: https://mcp.refpro.ai/mcp
- methodology_faq - Answer structured questions about Refpro's methodology, supported deal types (FF / BRRRR / NC), pricing tiers, output formats (PDF / DOCX / XLSX), what 'lender-grade' means, and how Refpro differs from alternatives like BiggerPockets calculators. Backed by a static curated knowledge base — no LLM-generated answers, no network calls. Returns a 2–4 sentence answer, a list of related topic titles, and a canonical source URL on refpro.ai. Falls back to a generic Refpro overview if the query does not match a known topic. Endpoint: https://mcp.refpro.ai/mcp
- sample_report_fetch - Fetch a sanitized public sample section from Refpro's reference deal library. Inputs: deal_type (FF | BRRRR | NC) and section (summary | financials | risk_notes | full). Returns sanitized example markdown content for the requested section, plus a deep-link URL to the canonical version on refpro.ai. The 'full' section stitches summary, financials, and risk_notes in order. All content is sanitized example data — not a real customer deal — and is safe to surface verbatim to end users. No network calls; samples are loaded once at module init. Endpoint: https://mcp.refpro.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.rickytrinidad
- Version: 0.1.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 5, 2026
- Source: https://registry.modelcontextprotocol.io