Construction Cost Calculator MCP
Provides construction cost estimation tools using data from a public Google Sheet for items like concrete, framing, and electrical. It allows users to search items, filter by category, and calculate total project costs including labor and material expenses.
README
Construction Cost Calculator MCP Server
A no-auth MCP (Model Context Protocol) server that provides construction cost estimation tools using data from a public Google Sheet.
Features
- No Authentication Required: Reads from a publicly accessible Google Sheet
- 5 Tools Available:
list_all_items- Get all construction itemsget_item- Get details for a specific item by codesearch_items- Search items by keywordget_items_by_category- Filter items by categorycalculate_cost- Calculate total project cost with quantities
Data Source
The server fetches construction cost data from this Google Sheet: Construction Cost Database
Data includes:
- Concrete (slabs, footings, walls, columns, stairs)
- Framing (walls, floors, roofs, beams)
- Finishes (drywall, paint, flooring, tile)
- Electrical (wiring, panels, outlets, fixtures)
- Plumbing (pipes, fixtures, water heaters)
- HVAC (systems, ductwork)
- Roofing (materials, installation)
- Exterior (siding, windows, doors)
Local Development
Prerequisites
- Python 3.11+
- pip
Setup
- Clone the repository:
cd construct_cost_calc
- Create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Run the server:
python server.py
The server will start on http://localhost:8000 with SSE transport.
Environment Variables
| Variable | Default | Description |
|---|---|---|
GOOGLE_SHEET_ID |
1laH5l1FjwWC5HXLp8xkG1eolwScKHIlxB6PohBWQjh0 |
Google Sheet ID |
SHEET_GID |
0 |
Sheet tab GID |
CACHE_TTL_SECONDS |
300 |
Cache duration (5 min) |
DEFAULT_LABOR_RATE |
75.0 |
Default $/hour rate |
Deploy to Render.com
One-Click Deploy
Manual Deploy
- Push this repository to GitHub
- Go to Render Dashboard
- Click New → Blueprint
- Connect your repository
- Render will use
render.yamlto configure the service
After Deployment
Your MCP server will be available at:
https://your-service-name.onrender.com/sse
Connect to Agenti AI Platform
Add the MCP server to your Agenti AI configuration:
{
"mcpServers": {
"construction-cost": {
"url": "https://your-service-name.onrender.com/sse"
}
}
}
Tool Usage Examples
List All Items
Tool: list_all_items
Parameters: none
Get Specific Item
Tool: get_item
Parameters: {"item_code": "concrete_slab_4000psi"}
Search Items
Tool: search_items
Parameters: {"query": "drywall"}
Get Items by Category
Tool: get_items_by_category
Parameters: {"category": "concrete"}
Calculate Cost
Tool: calculate_cost
Parameters: {
"items": [
{"item_code": "concrete_slab_4000psi", "quantity": 2000},
{"item_code": "framing_wall_2x4", "quantity": 500},
{"item_code": "drywall_standard_12", "quantity": 3000}
],
"labor_rate": 80.0
}
Cost Calculation Formula
Item Cost = (Material Cost × Quantity) + (Labor Hours × Quantity × Labor Rate)
Total Cost = Sum of all Item Costs
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。