MCP Personal Tools Server

MCP Personal Tools Server

A simple server implementing the Model Context Protocol (MCP) that exposes personal tools like note-taking for compatible MCP clients or agents.

Category
访问服务器

Tools

add-note

Ajoute une nouvelle ligne au fichier de notes

README

MCP Personal Tools Server

This project is a simple server that implements the Model Context Protocol (MCP). It exposes a set of personal tools that can be used by a compatible MCP client or agent. The initial tool allows for adding notes to a local file.

Features

  • Model Context Protocol (MCP) Server: Built using the @modelcontextprotocol/sdk.
  • Extensible Toolset: Designed to be easily extended with new custom tools.
  • Note-Taking Tool: Includes a simple add-note tool to append text to a notes file.

Prerequisites

  • Node.js (v18 or later recommended)
  • npm (usually comes with Node.js)

Installation

  1. Clone the repository or set up the project files.
  2. Install the required dependencies:
    npm install
    

Usage

There are several ways to run the server.

Development Mode

To run the server with hot-reloading for development, use:

npm run server:dev

Production

  1. Build the TypeScript code: This command compiles the src/server.ts file into JavaScript in the build directory.

    npm run build
    
  2. Start the server: This command runs the compiled server.

    npm start
    

Inspecting the Server

The Model Context Protocol includes an inspector tool to view the server's capabilities (like the tools it offers). To use it, run:

npm run server:inspect

This will start your server and open the inspector, allowing you to see the available tools and their schemas.

Available Tools

add-note

  • Description: Adds a new line with a timestamp to a notes file.
  • Parameters:
    • text (string): The text content to add to the note.
  • File Location: The notes are stored in a file named note.txt located in ~/Documents/notes/. The directory is created automatically if it does not exist.

How to Add a New Tool

You can easily add new tools to the server by following the pattern in src/server.ts.

  1. Open src/server.ts.
  2. Use the server.tool() method to define your new tool.
  3. Provide a name, a description, a Zod schema for the input parameters, and an async function to execute the tool's logic.

Example

server.tool("new-tool-name", "A description of what the new tool does.", {
    // Define input parameters using Zod
    param1: z.string().describe("Description for param1"),
    param2: z.boolean().describe("Description for param2"),
}, {
    // Tool metadata (optional but recommended)
    title: "New Tool Title",
    readOnlyHint: false,
    destructiveHint: false,
    idempotentHint: false,
    openWorldHint: true,
}, async ({ param1, param2 }) => {
    // Your tool's logic here
    console.log(`Executing with: ${param1} and ${param2}`);
    
    // Return a result
    return {
        content: [{ type: "text", text: "New tool executed successfully!" }]
    };
})

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