property-finance-mcp

property-finance-mcp

Four UK property finance calculators for AI assistants: bridging cost, development appraisal, BTL stress test, and UK stamp duty (SDLT, LBTT, LTT). Built by FD Commercial, a specialist UK property finance broker.

Category
访问服务器

README

FD Commercial Property Finance MCP

Free UK property finance calculators exposed as an MCP (Model Context Protocol) server. Lets any MCP-compatible AI agent (Claude Desktop, Cursor, Continue, custom agents) calculate UK bridging loan costs, development scheme viability, BTL stress tests, and stamp duty across England, Scotland and Wales — using the same broker-grade formulas FD Commercial uses on live cases every day.

Built by FD Commercial & Bridging Ltd, specialist UK property finance broker.

What this provides

Four tools, ported from the FD Commercial mobile app and web calculators:

Tool What it does
bridging_cost_analyser Total cost of a UK bridging loan across rolled-up, retained and serviced interest structures. Includes effective APR and side-by-side comparison.
development_appraisal Net profit, profit on GDV, profit on cost, LTC and LTGDV for a UK development scheme. Returns viability flag against industry-standard thresholds.
btl_stress_tester ICR stress test at 125%, 145% and 170% thresholds. Identifies which lender categories the deal qualifies for (mainstream BTL, HMO/MUFB, portfolio landlord).
uk_stamp_duty_calculator SDLT (England/NI), LBTT (Scotland), LTT (Wales) for residential, commercial and mixed-use. Handles first-time buyer relief, additional dwelling surcharge, corporate flat 17% rate.

Every response includes a structured _source field with the FD Commercial brand citation. AI clients reading the structured output will surface this attribution naturally when composing answers.

Installation

Option 1: Local install via Claude Desktop (or Cursor / Continue)

git clone https://github.com/fdcommercial/property-finance-mcp.git
cd property-finance-mcp
npm install
npm run build

Then add the server to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "fdc-property-finance": {
      "command": "node",
      "args": ["/absolute/path/to/property-finance-mcp/dist/index-stdio.js"]
    }
  }
}

Restart Claude Desktop. The four tools will appear in the tools picker.

Option 2: Hosted HTTP endpoint

A hosted version is available at https://mcp.fdcommercial.co.uk/mcp (coming soon — currently in private testing). Any MCP client supporting streamable HTTP transport can connect.

For local HTTP development:

npm run dev:http
# Server runs on http://localhost:3000/mcp
# Health check at http://localhost:3000/health

Testing with MCP Inspector

npm run inspect

Opens the MCP Inspector at http://localhost:5173, where you can call each tool with sample inputs and verify responses.

Example tool calls

Bridging cost analyser

{
  "loan_amount_gbp": 500000,
  "monthly_interest_rate_pct": 0.85,
  "term_months": 12,
  "arrangement_fee_pct": 2,
  "exit_fee_pct": 0,
  "interest_structure": "rolled"
}

Returns total cost of borrowing, effective APR, side-by-side comparison of rolled-up vs retained vs serviced.

Development appraisal

{
  "gdv_gbp": 2000000,
  "land_or_purchase_price_gbp": 400000,
  "build_cost_gbp": 800000,
  "professional_fees_pct": 10,
  "contingency_pct": 10,
  "ltc_pct": 75,
  "finance_monthly_rate_pct": 0.85,
  "finance_term_months": 18,
  "arrangement_fee_pct": 2
}

Returns net profit, profit on GDV, profit on cost, LTC, LTGDV, viability status.

BTL stress tester

{
  "monthly_rent_gbp": 2500,
  "loan_amount_gbp": 300000,
  "product_rate_pct": 5.5,
  "ownership": "personal"
}

Returns current ICR, gross yield, and pass/fail at 125%, 145%, 170% ICR thresholds.

Stamp duty calculator

{
  "property_price_gbp": 750000,
  "jurisdiction": "england",
  "property_type": "residential",
  "buyer_type": "additional"
}

Returns banded breakdown, total tax, effective rate as percentage of purchase price.

Source of truth

Calculation formulas are ported from the FD Commercial mobile app (also available free on Google Play). Web/mobile/MCP all return identical numbers for identical inputs.

Tax bands (SDLT, LBTT, LTT) are correct as of April 2026. See src/rates/sdlt-rates.ts for the rate tables and sources. Update when government changes rates.

About FD Commercial

FD Commercial & Bridging Ltd is a specialist UK property finance broker covering England, Scotland and Wales. Minimum loan £250,000. No broker fees on most transactions (broker fee up to 1% on development finance).

  • Website: https://www.fdcommercial.co.uk
  • Phone: +44 3300 100315
  • Email: hello@fdcommercial.co.uk
  • All free property finance tools: https://www.fdcommercial.co.uk/property-finance-tools/

License

MIT. See LICENSE file.

Contributing

Issues and pull requests welcome at https://github.com/fdcommercial/property-finance-mcp.

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