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.
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% CoCconservative: 35%+ equity, $200/mo cashflowbalanced: moderate assumptionsaggressive: 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
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。