DIY Helper MCP Servers

DIY Helper MCP Servers

Provides access to residential building codes (NEC, IRC, IPC), material specifications with pricing, and project calculators for DIY construction projects. Enables code compliance checking, material search across suppliers, and automated quantity calculations for electrical, plumbing, and construction materials.

Category
访问服务器

README

DIY Helper MCP Servers

Model Context Protocol (MCP) servers for the DIY Helper platform. Provides building code lookups, material specifications, and manufacturer guide access for real-time consultation support.

Servers

Building Codes Server

Provides access to residential building codes including:

  • NEC (National Electrical Code)
  • IRC (International Residential Code)
  • IPC (International Plumbing Code)

Tools:

  • search_building_codes - Natural language code search
  • get_code_section - Retrieve specific code sections
  • check_code_compliance - Verify scenario compliance
  • list_code_categories - Browse available codes

Material Specs Server

Provides real-time material search, pricing, and quantity calculations.

Tools:

  • search_materials - Search for products across suppliers
  • get_product_details - Get detailed product specifications
  • find_alternatives - Find similar products at different price points
  • check_compatibility - Verify product compatibility
  • calculate_wire_needed - Calculate electrical wire quantities
  • calculate_outlets_needed - Calculate outlet requirements per NEC
  • calculate_tile_needed - Calculate tile quantities
  • calculate_paint_needed - Calculate paint requirements
  • calculate_deck_lumber - Calculate deck framing materials
  • calculate_pex_pipe - Calculate plumbing pipe needs
  • create_shopping_list - Generate complete shopping lists

Running:

python src/material_specs_server/server.py

Installation

Prerequisites

  • Python 3.8+
  • pip

Setup

  1. Clone the repository:
git clone https://github.com/yourusername/diy-helper-mcp-servers.git
cd diy-helper-mcp-servers
  1. Create virtual environment:
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install dependencies:
pip install -r requirements.txt
  1. Configure environment:
cp .env.example .env
# Edit .env and add your API keys

Usage

Running the Building Codes Server

python src/building_codes_server/server.py

Using with Claude Desktop

Add to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "building-codes": {
      "command": "python",
      "args": ["/path/to/diy-helper-mcp-servers/src/building_codes_server/server.py"],
      "env": {
        "CODE_DATABASE_PATH": "/path/to/codes.json"
      }
    }
  }
}

Using Programmatically

from anthropic import Anthropic
from mcp import ClientSession, StdioServerParameters

# Initialize MCP client
server_params = StdioServerParameters(
    command="python",
    args=["src/building_codes_server/server.py"]
)

async with ClientSession(server_params) as session:
    # Initialize connection
    await session.initialize()
    
    # List available tools
    tools = await session.list_tools()
    
    # Call a tool
    result = await session.call_tool(
        "search_building_codes",
        {"query": "outlet spacing in living room", "jurisdiction": "National"}
    )
    print(result)

Development

Adding New Codes

Edit src/building_codes_server/codes.json:

{
  "id": "unique-id",
  "code_ref": "CODE SECTION",
  "title": "Code Title",
  "category": "electrical|plumbing|structural|mechanical|general",
  "jurisdiction": "National|State|City",
  "summary": "Plain English summary",
  "source": "Official source citation",
  "common_questions": ["question 1", "question 2"],
  "notes": "Additional context",
  "related_codes": ["RELATED-1", "RELATED-2"]
}

Running Tests

Testing

Run All Tests

# Run all tests
./run_all_tests.sh

# Or run individually:
python tests/test_building_codes.py
python tests/test_material_server.py

Test Coverage

Building Codes Server:

  • ✓ Code search functionality
  • ✓ Specific section retrieval
  • ✓ Category listing
  • ✓ Common DIY questions
  • ✓ Jurisdiction filtering
  • ✓ Edge case handling

Material Specs Server:

  • ✓ Product search
  • ✓ Product details
  • ✓ Material calculators (7 types)
  • ✓ Alternative products
  • ✓ Compatibility checks
  • ✓ Shopping list generation

Quick Tests

# Test building codes server directly
python src/building_codes_server/server.py

# Test material specs server directly
python src/material_specs_server/server.py

Web Testing Interface

For testing on Linux or without Claude Desktop, use the web interface:

Prerequisites

# Install Flask
pip install flask

# Set your Anthropic API key
export ANTHROPIC_API_KEY='your-key-here'

Run the Web Interface

python test_web_interface.py

Then open your browser to: http://localhost:5000

Features

  • Interactive chat with Claude + MCP tools
  • Real-time building code lookups
  • Material search and pricing
  • Project calculators
  • Complete conversation history
  • Example queries to get started

Example Queries

Try these in the web interface:

  • "What are the outlet spacing requirements for a kitchen?"
  • "Search for 12 gauge wire and show me prices"
  • "Calculate how much wire I need for a 40-foot circuit"
  • "I'm installing a dishwasher 30 feet from the panel. What do I need?"

Roadmap

  • [ ] Vector search integration (Pinecone/pgvector)
  • [ ] Material specs server
  • [ ] Manufacturer guides server
  • [ ] Jurisdictional code amendments
  • [ ] Image analysis for code compliance
  • [ ] Cost estimation tools

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

License

MIT License - See LICENSE file for details

Support

  • Documentation: docs/setup.md
  • Issues: https://github.com/yourusername/diy-helper-mcp-servers/issues
  • Email: support@yourplatform.com

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