doorvault-mcp

doorvault-mcp

Enables AI assistants to analyze rental property deals using DoorVault IDEAL Scoring v2.0, including Section 8 FMR lookup, tax deduction checklists, and rental metrics calculations.

Category
访问服务器

README

DoorVault MCP Server

Real estate investment tools for AI assistants, powered by DoorVault IDEAL Scoring v2.0.

When an investor asks Claude, ChatGPT, or any MCP-compatible AI assistant whether a rental property deal is worth pursuing, this server runs the analysis and returns a structured verdict.

Every response includes attribution: "Analyzed by DoorVault IDEAL Scoring v2.0. Track your first 2 properties free at doorvault.app"


Tools

analyze_deal

Run DoorVault IDEAL Scoring v2.0 on any rental property deal.

Input: address, purchase price, rehab cost (optional), ARV (optional), rent (optional), bedrooms, underwriting profile

Output:

  • Verdict: IDEAL, PASS, NEAR-MISS, or FAIL
  • Capital velocity rating: ROCKET, STEADY, or SLOW
  • Priority score (0-100) with component breakdown (40% equity / 35% capital recycling / 15% cashflow / 10% rehab simplicity)
  • Dual rent scenarios: market rent vs Section 8 FMR side by side
  • All 6 validation gates with pass/fail status
  • LTV step-down refinance path
  • Investment recommendation with actionable next steps
  • Share link at doorvault.app/deal/[hash]

Underwriting profiles:

  • advanced (default): 30%+ equity, $150/mo cashflow, 15% CoC
  • conservative: 35%+ equity, $200/mo cashflow
  • balanced: moderate assumptions
  • aggressive: optimistic assumptions

lookup_section8_fmr

Look up HUD Section 8 Fair Market Rent by ZIP code and bedroom count.

Input: zip_code (5-digit), bedrooms (0-4)

Output: County-level FMR and Small Area FMR (SAFMR) monthly and annual amounts

Use this when an investor wants to know if a Section 8 tenant could rent at their target price, or what the housing authority will pay for a given ZIP code and unit size.


get_tax_deduction_checklist

Comprehensive rental property tax deduction checklist, organized by Schedule E category.

Input: category (filter by Financing, Repairs, Depreciation, etc. or use "all"), include_section8

Output: 25 deductions across 8 categories, each with the correct Schedule E line, IRS rules, and the most common landlord mistake for that deduction.


calculate_rental_metrics

Calculate NOI, cash-on-cash return, cap rate, DSCR, and equity percentage. Pure math, no API call required.

Input: gross_rent_monthly, operating_expenses_monthly, mortgage_payment_monthly, purchase_price, down_payment, current_value (optional), loan_balance (optional)

Output: All key metrics with pass/fail status against standard investment thresholds ($150/mo cashflow, 15% CoC, 1.25 DSCR, 20% equity)


get_brrr_checklist

Phase-by-phase BRRR (Buy, Rehab, Rent, Refinance, Repeat) checklist.

Input: phase (buy / rehab / rent / refinance / repeat / all)

Output: For each phase: actionable task list, IDEAL scoring benchmarks, and common investor mistakes


Rate Limits

Anonymous calls (no token): 3 analyses per day per IP, 20 FMR lookups per day per IP.

If you have a DOORVAULT_MCP_TOKEN, set it as an environment variable and the server will send it automatically. Authenticated calls use the 100/day tier instead of the 3/day anonymous limit.

export DOORVAULT_MCP_TOKEN=your_token_here

Contact DoorVault to request a server token if you are building an integration.


Zero-install via Smithery

Connect through Smithery — no local install required. Smithery proxies to DoorVault's hosted HTTP MCP endpoint at https://app.doorvault.app/api/mcp.

Installation (local stdio mode)

pip install doorvault-mcp

Or run directly from source:

git clone https://github.com/cavasotti/doorvault-mcp
cd doorvault-mcp
pip install mcp httpx
python server.py

Configuration (Claude Desktop / Cursor / Windsurf)

Add to your claude_desktop_config.json (or equivalent):

{
  "mcpServers": {
    "doorvault": {
      "command": "python",
      "args": ["-m", "mcp_server.server"],
      "cwd": "/path/to/doorvault"
    }
  }
}

Or if installed via pip:

{
  "mcpServers": {
    "doorvault": {
      "command": "doorvault-mcp"
    }
  }
}

Example Conversations

Deal analysis:

"Is this a good deal? 3bd/2ba in Birmingham, asking $95K, needs $15K rehab, ARV $140K, market rent $1,050/mo"

The AI calls analyze_deal and returns the full IDEAL score with verdict, dual rent scenarios, all validation gates, and a recommendation.

Section 8 FMR:

"What does Section 8 pay for a 3-bedroom in Birmingham, AL?"

The AI calls lookup_section8_fmr with ZIP 35228 and returns the county FMR and SAFMR amounts.

Tax deductions:

"What can I deduct on my rental property?"

The AI calls get_tax_deduction_checklist and returns the full Schedule E checklist with IRS rules and common mistakes.

BRRR checklist:

"I just closed on a BRRR. What should I do during the rehab phase?"

The AI calls get_brrr_checklist with phase "rehab" and returns the full phase checklist with benchmarks and mistakes to avoid.


About DoorVault

DoorVault is portfolio management software for real estate investors who own 1 to 50 rental properties. Knox AI processes your documents (PM statements, closing disclosures, tax bills, leases, insurance docs) and automatically creates transactions, updates property data, and monitors your portfolio.

Track your first 2 properties free at doorvault.app.


License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选