
Build MCP Server
Enables AI assistants to manage development workflows by running build commands, executing tests, analyzing package.json files, installing dependencies, and performing code linting. Supports multiple package managers (npm, yarn, pnpm) and provides detailed error reporting for development operations.
README
Build MCP Server
A Model Context Protocol (MCP) server that provides build and development tools for AI assistants. This server enables AI agents to run build commands, tests, linting, and manage dependencies in development projects.
Features
- Build Management: Run build commands with customizable parameters
- Test Execution: Execute test suites and report results
- Package Analysis: Read and analyze package.json files
- Dependency Management: Install dependencies using npm, yarn, or pnpm
- Code Linting: Run linting tools and report code quality issues
Installation
From GitHub (Recommended)
npx build-mcp-server
Local Development
git clone <your-repo-url>
cd build-mcp-server
npm install
npm run build
Configuration
Add this server to your MCP configuration file:
{
"mcpServers": {
"build-server": {
"command": "npx",
"args": [
"-y",
"build-mcp-server"
],
"env": {}
}
}
}
Or for local development:
{
"mcpServers": {
"build-server": {
"command": "node",
"args": [
"/path/to/build-mcp-server/dist/index.js"
],
"env": {}
}
}
}
Available Tools
run_build
Execute build commands in a project directory.
Parameters:
command
(string, optional): Build command to run (default: "npm run build")directory
(string, optional): Directory to run the build in (default: current directory)
Example:
Run build command "npm run build" in the current directory
run_test
Execute test suites in a project directory.
Parameters:
command
(string, optional): Test command to run (default: "npm test")directory
(string, optional): Directory to run tests in (default: current directory)
Example:
Run tests using "yarn test" in the ./frontend directory
check_package_json
Analyze package.json files and extract key information.
Parameters:
directory
(string, optional): Directory containing package.json (default: current directory)
Example:
Check package.json in the current directory
install_dependencies
Install project dependencies using various package managers.
Parameters:
manager
(string, optional): Package manager to use - npm, yarn, or pnpm (default: "npm")directory
(string, optional): Directory to install dependencies in (default: current directory)
Example:
Install dependencies using yarn in the ./backend directory
lint_code
Run code linting and quality checks.
Parameters:
command
(string, optional): Lint command to run (default: "npm run lint")directory
(string, optional): Directory to run linting in (default: current directory)
Example:
Run linting with "eslint ." command
Usage Examples
Once configured, you can use natural language to interact with the build server:
- "Build the project"
- "Run tests in the frontend directory"
- "Install dependencies using yarn"
- "Check what scripts are available in package.json"
- "Lint the code and show me any issues"
Error Handling
The server provides detailed error messages and output for all operations. Build failures, test errors, and linting issues are clearly reported with full context.
Security
This server executes shell commands in the specified directories. Ensure you trust the environment and commands being executed. The server includes timeout protections to prevent long-running processes.
Development
To contribute or modify the server:
# Clone and install
git clone <repo-url>
cd build-mcp-server
npm install
# Development with auto-reload
npm run dev
# Build for production
npm run build
# Test the server
npm start
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。