Discover Awesome MCP Servers
Extend your agent with 20,542 capabilities via MCP servers.
- All20,542
- Developer Tools3,867
- Search1,714
- Research & Data1,557
- AI Integration Systems229
- Cloud Platforms219
- Data & App Analysis181
- Database Interaction177
- Remote Shell Execution165
- Browser Automation147
- Databases145
- Communication137
- AI Content Generation127
- OS Automation120
- Programming Docs Access109
- Content Fetching108
- Note Taking97
- File Systems96
- Version Control93
- Finance91
- Knowledge & Memory90
- Monitoring79
- Security71
- Image & Video Processing69
- Digital Note Management66
- AI Memory Systems62
- Advanced AI Reasoning59
- Git Management Tools58
- Cloud Storage51
- Entertainment & Media43
- Virtualization42
- Location Services35
- Web Automation & Stealth32
- Media Content Processing32
- Calendar Management26
- Ecommerce & Retail18
- Speech Processing18
- Customer Data Platforms16
- Travel & Transportation14
- Education & Learning Tools13
- Home Automation & IoT13
- Web Search Integration12
- Health & Wellness10
- Customer Support10
- Marketing9
- Games & Gamification8
- Google Cloud Integrations7
- Art & Culture4
- Language Translation3
- Legal & Compliance2
Netlify Express MCP Server
A basic serverless MCP implementation using Netlify Functions and Express. Demonstrates how to deploy and run Model Context Protocol servers in a serverless environment with proper routing configuration.
Remote MCP Server on Cloudflare
Modular Search MCP
A VS Code extension that integrates DuckDuckGo web search capabilities with GitHub Copilot Chat through a Model Context Protocol server.
MCP SSH Agent
A server that enables secure interaction with remote SSH hosts through standardized MCP interface, providing functions like listing hosts, executing commands, and transferring files using native SSH tools.
DeSo MCP Server
A comprehensive Model Context Protocol server that transforms Cursor's AI assistant into a DeSo blockchain development expert, providing complete API coverage, debugging solutions, and code generation for DeSo applications.
mcp-micromanage
開発ワークフローのためのマイクロマネジメントツール:コーディングエージェントが、詳細なコミットレベルの粒度で、連続的な開発タスクを計画、追跡、可視化するのを支援します。インタラクティブな可視化、自動化されたステータス追跡、構造化されたワークフロー管理機能を備えています。
lafe-blog MCP Server
Enables creating and managing text notes with a simple note-taking system. Provides tools to create notes, access them via URIs, and generate summaries of all stored notes.
NCP MCP Server
Enables conversational management of Naver Cloud Platform infrastructure through Claude Desktop, allowing users to create, query, and manage cloud resources like servers, VPCs, load balancers, and databases using natural language.
Remote MCP Server (Authless)
Deploys a Model Context Protocol server on Cloudflare Workers without authentication requirements, allowing you to create and expose custom AI tools to clients like Claude Desktop or Cloudflare AI Playground.
MCP Server MySQL
Enables LLMs to interact with MySQL databases through standardized protocol, supporting database management, table operations, data queries, and modifications with configurable permission controls.
OpsNow MCP Asset Server
Neil Mcp Server Include Mysql
include: mcp-mysql
ai-scheduler-mcp
Google Tasks API と Google Calendar API を利用した、スケジューリング用の SSE (Server-Sent Events) 対応の MCP (Microservices Communication Platform) サーバーですね。 日本語として自然になるように、少し言い換えてみます。 **より自然な表現:** Google Tasks API と Google Calendar API を活用し、SSE (Server-Sent Events) に対応した、スケジューリング用マイクロサービス連携プラットフォーム (MCP) サーバー **さらに具体的にする場合:** Google Tasks API と Google Calendar API を利用して、タスクとカレンダーを連携させたスケジューリングシステムを構築するための、SSE (Server-Sent Events) 対応マイクロサービス連携プラットフォーム (MCP) サーバー **ポイント:** * "スケジューリング用" を "スケジューリングシステムを構築するための" のように具体的にすると、より意図が伝わりやすくなります。 * "mcp server" を "マイクロサービス連携プラットフォーム (MCP) サーバー" とすることで、より専門的な印象を与えられます。 どちらの表現が良いかは、文脈や対象読者によって異なります。
MCPLab
MCP (Model Context Protocol) のサーバー・クライアントの例、コード、設計、チュートリアルについてですね。 日本語で情報を見つけるのは難しいかもしれませんが、英語であれば以下のキーワードで検索すると関連情報が見つかる可能性があります。 * "Model Context Protocol examples" * "MCP server client tutorial" * "MCP design patterns" * "MCP implementation" もし具体的なMCPのライブラリやフレームワークの名前が分かれば、それらと組み合わせて検索すると、より的確な情報が見つかるかもしれません。 例えば、もし特定のプログラミング言語 (Python, Java, C++など) での実装例を探しているのであれば、"MCP Python example" のように言語名を追加すると良いでしょう。 もしMCPについて具体的な質問があれば、詳細を教えていただけると、より的確な情報を提供できるかもしれません。
Water Bar Email MCP Server
Enables sending branded wellness booking confirmation emails through Resend integration. Supports multiple email flows including AOI experience bookings with AI-suggested drink pairings and timeline layouts.
Thoughtspot
Thoughtspot
Email MCP Server
これは、複数のメールプロトコルと機能をサポートする、メール通信を処理するために設計されたMCPサーバーです。
Weather MCP Server
Anki MCP Server
A Model Context Protocol server that bridges Claude AI with Anki flashcard app, allowing users to create and manage flashcards using natural language commands.
MCP File Operations Server
Enables secure file management operations within a documents folder, including reading, writing, listing, deleting files and creating directories. Supports all file types with path validation to prevent access outside the designated documents directory.
XHS MCP
Enables interaction with Xiaohongshu (Little Red Book) platform through automated browser operations. Supports authentication, content publishing, search, discovery, and commenting using Puppeteer-based automation.
Robot Navigation MCP Server
Enables robot navigation control and monitoring through natural language. Provides tools for robot positioning, navigation to coordinates, device status monitoring, task management, and emergency controls.
MCP Chat with Claude
Okay, here's a TypeScript example for a web app (acting as the host) connecting to a Node.js MCP (Mesh Control Protocol) server. This example focuses on the core connection and message exchange. It assumes you have a basic understanding of TypeScript, Node.js, and web development. **Important Considerations:** * **MCP Library:** This example uses a hypothetical `mcp-client` library. You'll likely need to adapt it to a real MCP library or implement your own MCP client logic. MCP is a protocol, and you'll need to handle the specific message formats and handshake procedures defined by your MCP implementation. * **Security:** In a production environment, you *must* consider security. Use secure WebSockets (WSS), authentication, and authorization to protect your MCP communication. * **Error Handling:** This example includes basic error handling, but you'll need to expand it to handle various network errors, MCP protocol errors, and unexpected situations. * **Framework:** This example uses vanilla TypeScript and assumes you'll integrate it into your web framework of choice (React, Angular, Vue, etc.). **1. Node.js MCP Server (Simplified Example - `mcp-server.ts`)** ```typescript // mcp-server.ts import WebSocket, { WebSocketServer } from 'ws'; const wss = new WebSocketServer({ port: 8080 }); wss.on('connection', ws => { console.log('Client connected'); ws.on('message', message => { console.log(`Received: ${message}`); // Process the MCP message (replace with your MCP logic) try { const parsedMessage = JSON.parse(message.toString()); // Assuming JSON format // Example: Echo back the message with a "response" field const response = { type: 'response', data: parsedMessage, status: 'ok' }; ws.send(JSON.stringify(response)); } catch (error) { console.error('Error processing message:', error); ws.send(JSON.stringify({ type: 'error', message: 'Invalid message format' })); } }); ws.on('close', () => { console.log('Client disconnected'); }); ws.on('error', error => { console.error('WebSocket error:', error); }); // Example: Send a welcome message ws.send(JSON.stringify({ type: 'welcome', message: 'Welcome to the MCP server!' })); }); console.log('MCP Server started on port 8080'); ``` **To run the server:** 1. Make sure you have Node.js and npm installed. 2. Create a directory for your project. 3. Save the code above as `mcp-server.ts`. 4. Open a terminal in the project directory. 5. Run: ```bash npm install ws # Install the WebSocket library npm install -D typescript @types/node @types/ws # Install TypeScript and type definitions npx tsc mcp-server.ts # Compile the TypeScript code node mcp-server.js # Run the compiled JavaScript ``` **2. Web App (TypeScript Client - `index.ts`)** ```typescript // index.ts (or your main TypeScript file) class MCPClient { private socket: WebSocket | null = null; private serverUrl: string; constructor(serverUrl: string) { this.serverUrl = serverUrl; } connect(): Promise<void> { return new Promise((resolve, reject) => { this.socket = new WebSocket(this.serverUrl); this.socket.addEventListener('open', () => { console.log('Connected to MCP server'); resolve(); }); this.socket.addEventListener('message', (event) => { console.log('Received:', event.data); this.handleMessage(event.data); }); this.socket.addEventListener('close', () => { console.log('Disconnected from MCP server'); this.socket = null; }); this.socket.addEventListener('error', (error) => { console.error('WebSocket error:', error); reject(error); }); }); } sendMessage(message: any): void { if (this.socket && this.socket.readyState === WebSocket.OPEN) { this.socket.send(JSON.stringify(message)); } else { console.warn('Not connected to MCP server. Message not sent.'); } } disconnect(): void { if (this.socket) { this.socket.close(); this.socket = null; } } private handleMessage(data: any): void { try { const message = JSON.parse(data); // Handle different message types based on your MCP protocol switch (message.type) { case 'welcome': console.log('Server says:', message.message); break; case 'response': console.log('Response from server:', message.data); break; case 'error': console.error('Error from server:', message.message); break; default: console.log('Unknown message type:', message); } } catch (error) { console.error('Error parsing message:', error); } } } // Example Usage (in your web app's main script) document.addEventListener('DOMContentLoaded', () => { const mcpClient = new MCPClient('ws://localhost:8080'); // Replace with your server URL const connectButton = document.getElementById('connectButton'); const sendButton = document.getElementById('sendButton'); const disconnectButton = document.getElementById('disconnectButton'); const messageInput = document.getElementById('messageInput') as HTMLInputElement; connectButton?.addEventListener('click', () => { mcpClient.connect().catch(error => { console.error('Failed to connect:', error); }); }); sendButton?.addEventListener('click', () => { const messageText = messageInput.value; try { const message = JSON.parse(messageText); mcpClient.sendMessage(message); } catch (error) { console.error("Invalid JSON message", error); } }); disconnectButton?.addEventListener('click', () => { mcpClient.disconnect(); }); }); ``` **3. HTML (Example - `index.html`)** ```html <!DOCTYPE html> <html> <head> <title>MCP Client</title> </head> <body> <h1>MCP Client</h1> <button id="connectButton">Connect</button> <button id="disconnectButton">Disconnect</button> <input type="text" id="messageInput" placeholder="Enter JSON message"> <button id="sendButton">Send Message</button> <script src="index.js"></script> <!-- Make sure this points to your compiled JavaScript file --> </body> </html> ``` **To run the web app:** 1. Save the code above as `index.ts` and `index.html` in the same directory. 2. Compile the TypeScript: ```bash npm install -D typescript @types/node # If you haven't already npx tsc index.ts ``` 3. This will create an `index.js` file. 4. Open `index.html` in your web browser. You'll need a simple web server to serve the HTML file correctly (e.g., using `npx serve .` or a similar tool). **Explanation:** * **`MCPClient` Class:** * Handles the WebSocket connection to the MCP server. * `connect()`: Establishes the WebSocket connection and sets up event listeners for `open`, `message`, `close`, and `error`. * `sendMessage()`: Sends a message to the server (after converting it to JSON). * `disconnect()`: Closes the WebSocket connection. * `handleMessage()`: Parses incoming messages and dispatches them based on their `type`. This is where you'll implement your MCP protocol logic. * **HTML:** * Provides buttons to connect, disconnect, and send messages. * An input field for entering JSON messages. * **Event Listeners:** * The `DOMContentLoaded` event ensures that the JavaScript code runs after the HTML is fully loaded. * Event listeners are attached to the buttons to call the `MCPClient` methods. **Key Improvements and Considerations:** * **MCP Protocol Implementation:** The `handleMessage()` function is the most important part to customize. You'll need to implement the specific message formats and logic defined by your MCP protocol. This might involve: * Defining TypeScript interfaces for your MCP message types. * Handling different commands and data structures. * Implementing error handling for invalid messages. * **Error Handling:** Add more robust error handling to catch network errors, invalid messages, and other unexpected situations. Consider using `try...catch` blocks and logging errors to the console or a logging service. * **Reconnection Logic:** Implement automatic reconnection logic in case the connection to the MCP server is lost. Use a backoff strategy to avoid overwhelming the server with reconnection attempts. * **Buffering Messages:** If the connection is temporarily lost, you might want to buffer messages and send them when the connection is re-established. * **Authentication/Authorization:** Implement authentication and authorization to ensure that only authorized clients can connect to the MCP server. This might involve using tokens, certificates, or other security mechanisms. * **Web Framework Integration:** Adapt this example to your chosen web framework (React, Angular, Vue, etc.). Use the framework's component model and data binding features to manage the MCP connection and display data. * **Asynchronous Operations:** Use `async/await` to handle asynchronous operations more cleanly. * **Testing:** Write unit tests and integration tests to ensure that your MCP client is working correctly. This comprehensive example provides a solid foundation for building a web app that connects to a Node.js MCP server using TypeScript. Remember to adapt it to your specific MCP protocol and security requirements.
MoluAbi MCP Server
Enables complete AI agent lifecycle management through MoluAbi's platform, allowing users to create, manage, and interact with AI assistants. Provides comprehensive tools for agent operations with secure authentication, usage tracking, and payment integration.
MCP Server Tester
Model Context Protocol (MCP) サーバー用の自動テストツール - 開発中
MCP Figma
Enables AI assistants to read and modify Figma designs programmatically, supporting design analysis, element creation, text replacement, annotations, auto-layout configuration, and prototype visualization through natural language commands.
MCP Server Directory
AIアプリケーション、開発、統合のためのモデルコンテキストプロトコルサーバーを見つけて共有しましょう。
mcp-server-twse
WarpGBM MCP Service
Provides GPU-accelerated gradient boosting model training and inference through a cloud service. Enables AI agents to train models on NVIDIA A10G GPUs and get fast cached predictions with portable model artifacts.
Oracle MCP Server
Oracleデータベース操作のためのモデルコンテキストプロトコル(MCP)サーバー実装