MCP Basics
A centralized Model Context Protocol server that provides common development tools (like formatting and translation) across all your Cline projects without needing to install them individually.
Tools
mcp-translator
Execute mcp-translator: npx ts-migrate
mcp-formatter
Execute mcp-formatter: npx prettier --write .
README
MCP Basics
A centralized Model Context Protocol (MCP) server that provides common development tools across all your Cline projects. Instead of installing tools individually in each project, use this single MCP server to access formatting, translation, and other development utilities.
Features
- mcp-formatter: Code formatting using Prettier (
npx prettier --write .) - mcp-translator: JavaScript to TypeScript migration (
npx ts-migrate) - Centralized tool management: Add tools once, use everywhere
- Directory-specific execution: Run tools in any project directory
Installation
- Clone this repository:
git clone https://github.com/caroline-davis/mcp-basics.git
cd mcp-basics
- Install dependencies:
npm install
- Test the server (optional):
node index.js
Configuration
In VSCode, set up your MCP settings and add Local MCP Basics as a new entry inside the mcpServers object:
Configuration:
{
"mcpServers": {
"Local MCP Basics": {
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "node",
"args": ["/path/to/mcp-basics/index.js"]
}
}
}
Replace /path/to/mcp-basics/index.js with the actual path to your cloned repository.
Usage
Once configured, you can use these tools in any Cline project by simply asking:
- "Use the mcp-formatter tool to format this code"
- "Run the mcp-translator tool to convert JavaScript to TypeScript"
- "Format the code using prettier"
The tools will execute in your current project directory automatically.
Tool Parameters
Each tool accepts an optional directory parameter:
// Example: Format code in a specific directory
{
"directory": "/path/to/specific/folder"
}
If no directory is specified, tools run in the current working directory.
Adding New Tools
To add new tools to the server:
- Edit
tools.jsonand add your tool:
[
{
"name": "your-tool-name",
"tool": "your-command-here"
}
]
- The tool will automatically be available in Cline without restarting.
Example: Adding ESLint
[
{
"name": "mcp-translator",
"tool": "npx ts-migrate"
},
{
"name": "mcp-formatter",
"tool": "npx prettier --write ."
},
{
"name": "mcp-linter",
"tool": "npx eslint . --fix"
}
]
Project Structure
mcp-basics/
├── index.js # Main MCP server implementation
├── tools.json # Tool configuration
├── package.json # Node.js dependencies
├── .gitignore # Git ignore rules
└── README.md # This file
Development
Running the Server
node index.js
The server will start and listen for MCP protocol messages via stdio.
Testing Tools
You can test individual tools by calling them through the MCP protocol or by running the commands directly:
# Test formatter
npx prettier --write .
# Test translator
npx ts-migrate
How It Works
This MCP server:
- Reads tool definitions from
tools.json - Exposes tools via the MCP protocol to Cline
- Executes commands in the specified directory when called
- Returns results with stdout, stderr, and execution status
Requirements
- Node.js (v14 or higher)
- npm or yarn
- Cline with MCP support
License
MIT License - feel free to use and modify as needed.
Contributing
- Fork the repository
- Add your tools to
tools.json - Test the changes
- Submit a pull request
Note: This server runs locally and doesn't require any external API keys or authentication. All tools execute using your local development environment.
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。