TradesPro
TradesPro is an open source MCP server that gives AI assistants structured knowledge of the skilled trades: electrical (NEC 2023), plumbing (UPC 2024), and HVAC (IRC Mechanical).
README
TradesPro MCP Server
An MCP (Model Context Protocol) server that gives AI assistants access to skilled trades knowledge — building codes, material pricing, job scoping, and permit requirements for electrical, plumbing, and HVAC work.
Why This Exists
AI assistants (Claude, ChatGPT, Cursor) can't look up building codes, estimate materials, or scope trade jobs accurately. This MCP server fixes that by giving agents structured, queryable access to:
- NEC 2023 electrical codes (GFCI, AFCI, wire sizing, panel requirements)
- UPC 2024 plumbing codes (drain sizing, venting, water heater sizing)
- IRC Mechanical HVAC codes (duct sizing, refrigerant lines, efficiency standards)
- Material pricing — 40+ common trade materials with national average prices
- Job templates — 8 standard residential jobs with labor, materials, and total pricing
- Permit checker — Determines if a described job likely requires permits
Quick Start
Install
pip install fastmcp
Run locally (stdio)
python server.py
Run as HTTP server
fastmcp run server.py:mcp --transport http --port 8000
Test with FastMCP Inspector
fastmcp dev server.py:mcp
This opens a web UI at http://127.0.0.1:6274 where you can test all tools interactively.
Connect to AI Clients
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"trades-pro": {
"command": "python",
"args": ["/path/to/server.py"]
}
}
}
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"trades-pro": {
"command": "python",
"args": ["/path/to/server.py"]
}
}
}
Remote (HTTP)
{
"mcpServers": {
"trades-pro": {
"url": "http://localhost:8000/mcp"
}
}
}
Available Tools
| Tool | Description |
|---|---|
lookup_building_code |
Look up specific code requirements (trade + topic) |
list_code_topics |
List all available code topics for a trade |
estimate_materials |
Get itemized material list and costs for a job |
scope_job |
Full job scope: labor, materials, price range, permits |
list_available_jobs |
Browse job templates, optionally filtered by trade |
lookup_material_price |
Search material pricing by keyword |
check_permit_requirements |
Check if a job description likely requires permits |
Example Queries
Once connected, ask your AI assistant:
- "What are the GFCI requirements for a kitchen remodel?"
- "Scope out a 200A panel upgrade — labor, materials, and total cost"
- "Do I need a permit to install an EV charger?"
- "What size wire do I need for a 50A circuit?"
- "Estimate materials for a bathroom rough-in"
Authentication & Pricing
TradesPro uses API key-based authentication with two tiers:
Free Tier (default)
- Access to all 7 tools — try everything before buying
- 10 calls per hour rate limit
- Use demo key
trades_demo_2026or connect without any key - Responses include a small footer with upgrade link
Pro Tier
- Unlimited access to all tools
- No rate limiting
- No footer messages
- Get your API key at bluecollar.run/pro
Configuring Your API Key
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"trades-pro": {
"url": "https://your-server-url.com/mcp",
"headers": {
"X-API-Key": "pk_your_api_key_here"
}
}
}
}
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"trades-pro": {
"url": "https://your-server-url.com/mcp",
"headers": {
"X-API-Key": "pk_your_api_key_here"
}
}
}
}
Free Tier (no key needed)
{
"mcpServers": {
"trades-pro": {
"url": "https://your-server-url.com/mcp"
}
}
}
Environment Variables
| Variable | Description | Default |
|---|---|---|
API_KEYS |
JSON string mapping API keys to tiers, e.g. {"pk_abc123": "pro"} |
"" (free tier only) |
PORT |
HTTP server port | 8000 |
Additional Monetization Options
xpay (Pay-per-call, zero code changes)
- Deploy the server as an HTTP endpoint
- Register at xpay.sh
- Set per-tool pricing ($0.01–$0.25 per call)
- Share the proxy URL instead of your direct server URL
B2B Retainer
Bundle this server with a custom AI agent for trade businesses:
- Charge $500–$2,000/month per client
- Customize data for their local market (local pricing, local codes)
- Add features: scheduling integration, invoice generation, CRM
Publishing to Smithery
npm install -g @smithery/cli
smithery mcp publish https://your-server-url.com/mcp -n your-org/trades-pro
Extending the Server
Add local pricing
Replace the MATERIAL_PRICES dict with data from local suppliers. The structure is simple:
"Item name": {"price": 0.00, "unit": "each", "category": "electrical"}
Add local code amendments
Many jurisdictions amend national codes. Add a local_amendments dict and modify lookup_building_code to layer local rules on top.
Add more job templates
Follow the JOB_TEMPLATES structure to add new jobs. Each template needs: name, trade, description, labor hours, materials list, permit info, and notes.
Hosting Options
| Option | Cost | Best For |
|---|---|---|
| Local (your machine) | Free | Development, personal use |
| Railway.app | ~$5/month | Cheap always-on hosting |
| Fly.io | ~$5/month | Edge deployment |
| Prefect Horizon | Free tier | FastMCP native hosting |
| Docker on VPS | ~$5-10/month | Full control |
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。