Notes Manager
A TypeScript-based MCP server that enables AI assistants to create, search, list, and delete notes with tags. Serves as a starter template for building custom MCP servers with tools and resources.
README
MCP Server: Notes Manager (TypeScript Starter)
A simple MCP (Model Context Protocol) server that manages notes. This is the companion repository for the Gheware DevOps AI YouTube tutorial: "Build Your Own MCP Server (TypeScript)".
What You'll Learn
- How to create an MCP server from scratch
- Implementing TOOLs (operations AI can perform)
- Implementing RESOURCEs (data AI can read)
- Testing with Claude Desktop and MCP Inspector
Features
Tools (AI Operations)
| Tool | Description |
|---|---|
add_note |
Create a new note with title, content, and tags |
list_notes |
List all notes with IDs and titles |
search_notes |
Search notes by title, content, or tags |
delete_note |
Delete a note by ID |
Resources (AI Data Access)
| URI | Description |
|---|---|
notes://list |
JSON list of all notes |
notes://note/{id} |
Individual note by ID |
Quick Start
Prerequisites
- Node.js 18+
- npm or yarn
- Claude Desktop (for testing)
Installation
# Clone the repository
git clone https://github.com/brainupgrade-in/mcp-server-typescript-starter.git
cd mcp-server-typescript-starter
# Install dependencies
npm install
# Build the project
npm run build
Test with MCP Inspector
npm run inspector
This opens a browser-based inspector to test your tools and resources.
Configure Claude Desktop
Add this to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"notes": {
"command": "node",
"args": ["/absolute/path/to/mcp-server-typescript-starter/dist/index.js"]
}
}
}
Restart Claude Desktop after saving.
Usage Examples
Once connected to Claude Desktop, try these prompts:
"Add a note about Docker networking with tags devops and docker"
"List all my notes"
"Search for notes about devops"
"Delete the welcome note"
Project Structure
mcp-server-typescript-starter/
├── src/
│ └── index.ts # Main MCP server code
├── dist/ # Compiled JavaScript (after build)
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # This file
Code Walkthrough
1. Server Setup
const server = new Server(
{ name: "notes-manager", version: "1.0.0" },
{ capabilities: { tools: {}, resources: {} } }
);
2. Defining a Tool
server.setRequestHandler(ListToolsRequestSchema, async () => ({
tools: [{
name: "add_note",
description: "Create a new note",
inputSchema: {
type: "object",
properties: {
title: { type: "string", description: "Note title" },
content: { type: "string", description: "Note content" }
},
required: ["title", "content"]
}
}]
}));
3. Handling Tool Calls
server.setRequestHandler(CallToolRequestSchema, async (request) => {
const { name, arguments: args } = request.params;
if (name === "add_note") {
// Create the note...
return { content: [{ type: "text", text: "Note created!" }] };
}
});
4. Exposing Resources
server.setRequestHandler(ListResourcesRequestSchema, async () => ({
resources: [{
uri: "notes://list",
name: "All Notes",
mimeType: "application/json"
}]
}));
Next Steps
- Add persistence (save notes to a file or database)
- Implement Prompts (pre-defined instruction templates)
- Add authentication for multi-user support
- Deploy as a standalone service
Resources
Video Tutorial
Watch the full tutorial on Gheware DevOps AI:
- What is MCP?
- MCP Architecture
- Install Your First MCP Server
- Build Your Own MCP Server ← This tutorial
License
MIT License - Feel free to use this as a starting point for your own MCP servers!
Made with ❤️ by Gheware DevOps AI
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。