io.github.rickytrinidad/refpro-mcp

Official3 toolsLive

by rickytrinidad

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

🛠️ Key Features

Name: io.github.rickytrinidad/refpro-mcp
Description focuses on deterministic underwriting, deal analysis, and reporting for real estate projects
Tool count: 3

🚀 Use Cases

Underwrite real estate deals with standardized assumptions
Generate deal analyses and performance reports for Fix & Flip, BRRRR, and construction projects
Support for deterministic evaluation workflows in real estate investment processes

⚡ Developer Benefits

Clear focus on underwriting, analysis, and reporting within a MCP server
Lightweight, three-tool footprint for streamlined integration
Suitable for cataloging in tech and real estate tooling ecosystems

⚠️ Limitations

Description limited to underwriting and reporting scope; no detailed feature list provided
No example prompts or documentation beyond the high-level description
No readme excerpt provided in source data

Captured live from the server via tools/list.

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.

Parameters9

deal_type	string	required
purchase_price	number	required
arv_or_value	number	required
rehab_budget	number	required
zip_code	string	required
annual_debt_service	number	optional
noi_annual	number	optional
units	integer	optional
units_to_hold	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "deal_type": {
      "type": "string",
      "enum": [
        "FF",
        "BRRRR",
        "NC"
      ]
    },
    "purchase_price": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000000000
    },
    "arv_or_value": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000000000
    },
    "rehab_budget": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000000000
    },
    "zip_code": {
      "type": "string",
      "pattern": "^\\d{5}$"
    },
    "annual_debt_service": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000000000
    },
    "noi_annual": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000000000
    },
    "units": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "units_to_hold": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "deal_type",
    "purchase_price",
    "arv_or_value",
    "rehab_budget",
    "zip_code"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

Parameters1

query

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

Parameters2

deal_type	string	required
section	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "deal_type": {
      "type": "string",
      "enum": [
        "FF",
        "BRRRR",
        "NC"
      ]
    },
    "section": {
      "type": "string",
      "enum": [
        "summary",
        "financials",
        "risk_notes",
        "full"
      ]
    }
  },
  "required": [
    "deal_type",
    "section"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Install

Tools (3)

deal_quick_checkmethodology_faqsample_report_fetch

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.refpro.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "refpro-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.refpro.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

deal_quick_check

methodology_faq

sample_report_fetch

Install

Remote endpoint

Related servers