Discover Awesome MCP Servers
Extend your agent with 50,638 capabilities via MCP servers.
- All50,638
- 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
Smartsheet MCP Server
Enables interaction with Smartsheet API to search, retrieve, create, update, and manage sheets, rows, webhooks, sharing permissions, cross-sheet references, and perform bulk operations through the Model Context Protocol.
Terminal Control MCP
Enables AI agents to interact with terminal-based TUI applications by capturing visual terminal output as PNG screenshots and simulating keyboard input through a virtual X11 display.
agoda-review-mcp
I'm sorry, I don't understand what you mean by "MCP server." Could you please rephrase your request? Are you looking for a way to find Agoda hotel reviews using a specific tool or method?
Jokes MCP Server
Provides access to various joke APIs including Chuck Norris jokes, Dad jokes, and Yo Mama jokes. Integrates with Microsoft Copilot Studio to create humor-focused agents that can deliver jokes on demand.
Accessibility Testing MCP
Enables accessibility testing of websites and HTML content using axe-core and IBM Equal Access engines. Supports WCAG compliance checking, multi-viewport testing, and provides detailed violation reports with remediation guidance.
ChatGPT Apps EdgeOne Pages Starter
A minimal MCP server template for deploying to Tencent Cloud EdgeOne Pages using Next.js and edge functions. Demonstrates tool registration and widget rendering with the hello_stat example tool.
STRING-MCP
A Model Context Protocol server that provides tools for interacting with the STRING database to analyze protein-protein interaction networks and functional enrichment. It enables users to map protein identifiers, retrieve interaction data, and generate biological network visualizations through natural language interfaces.
Video Convert MCP
A professional video format conversion tool based on MCP protocol that supports multiple formats, batch processing, and quality control for video files.
BlindPay MCP Server
Enables AI assistants to interact with BlindPay's stablecoin payment infrastructure, allowing users to create receivers, process payouts and payins across multiple blockchains, manage virtual accounts and wallets, and configure payment operations through natural language.
M/M/1 and M/M/c Queue Simulation Server
Enables simulation and analysis of M/M/1 and M/M/c queuing systems using SimPy, with tools for parameter validation, theoretical metric calculation, simulation execution, and comparison of separate vs pooled queue strategies.
Octagon VC Agents
An MCP server that runs AI-driven venture capitalist agents whose thinking is continuously enriched by Octagon Private Markets' real-time deals and intelligence for pitch feedback, diligence simulations, and term sheet negotiations.
Twilio MCP
Enables sending SMS text messages through Twilio's messaging service with a simple send_text tool that supports configurable recipients and messaging service integration.
Mcp Cassandra Server
Okay, here's the translation of "Model Context Protocol for Cassandra database" into Vietnamese, along with some considerations for different nuances: **Option 1 (Most Direct Translation):** * **Giao thức Ngữ cảnh Mô hình cho cơ sở dữ liệu Cassandra** * This is a very literal translation. It's understandable, but might sound a bit technical and formal. **Option 2 (More Natural, Emphasizing Purpose):** * **Giao thức Ngữ cảnh Mô hình cho cơ sở dữ liệu Cassandra** * This is a more natural way to phrase it in Vietnamese. **Option 3 (If you want to emphasize the "Model Context" as a specific thing):** * **Giao thức Ngữ cảnh Mô hình (Model Context) cho cơ sở dữ liệu Cassandra** * This keeps the English term in parentheses to clarify that "Model Context" is a specific concept. **Explanation of Terms:** * **Protocol:** Giao thức * **Model:** Mô hình * **Context:** Ngữ cảnh * **Database:** Cơ sở dữ liệu * **Cassandra:** Cassandra (usually kept as is, as it's a proper name) **Which option to choose depends on the context in which you're using the phrase:** * If you're writing for a highly technical audience already familiar with the term "Model Context," Option 1 is fine. * If you want to make it more accessible, Option 2 is better. * If you think your audience might not be familiar with "Model Context" as a specific term, Option 3 is the safest. I hope this helps! Let me know if you have any other questions.
NervusDB MCP Server
Enables building and querying code knowledge graphs for project analysis, with tools for exploring code relationships, managing workflows, and automating development tasks. Integrates with Git and GitHub for branch management and pull request creation.
MCP Server Boilerplate
A starter template for building Model Context Protocol servers that can integrate with AI assistants like Claude or Cursor, providing custom tools, resource providers, and prompt templates.
sheet-music-mcp
Máy chủ MCP để hiển thị bản nhạc
MCP 만들면서 원리 파헤쳐보기
Okay, here's a breakdown of a server and client implementation for a system conceptually similar to the MCP (Master Control Program), along with considerations for a Vietnamese audience. I'll focus on the core concepts and provide examples using Python, a widely accessible language. Remember that a *true* MCP is a complex operating system kernel, so this is a simplified, illustrative example. **Conceptual Overview** The MCP, in its essence, is a central control point. In a modern context, we can think of it as a central server managing resources, tasks, and communication between multiple clients. * **Server (MCP):** * Listens for client connections. * Authenticates clients (optional, but important for security). * Manages a queue of tasks or requests. * Allocates resources (e.g., processing time, memory, data access). * Monitors system health and performance. * Provides a central logging and auditing facility. * Can enforce security policies. * **Client:** * Connects to the server. * Authenticates itself (if required). * Submits tasks or requests to the server. * Receives results or status updates from the server. * Handles errors and retries. **Python Implementation (Simplified)** This example uses Python's `socket` library for basic network communication and `threading` for handling multiple clients concurrently. **1. Server (mcp_server.py):** ```python import socket import threading import time HOST = '127.0.0.1' # Standard loopback interface address (localhost) PORT = 65432 # Port to listen on (non-privileged ports are > 1023) def handle_client(conn, addr): """Handles communication with a single client.""" print(f"Connected by {addr}") try: while True: data = conn.recv(1024) # Receive data from the client if not data: break # Client disconnected message = data.decode('utf-8') print(f"Received from {addr}: {message}") # **Simulated Task Processing** time.sleep(2) # Simulate some work being done response = f"MCP: Task '{message}' processed successfully." conn.sendall(response.encode('utf-8')) except ConnectionResetError: print(f"Client {addr} disconnected abruptly.") finally: conn.close() print(f"Connection with {addr} closed.") def main(): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() print(f"MCP Server listening on {HOST}:{PORT}") while True: conn, addr = s.accept() # Accept incoming connections thread = threading.Thread(target=handle_client, args=(conn, addr)) thread.start() print(f"Active Connections: {threading.active_count() - 1}") #Subtract main thread if __name__ == "__main__": main() ``` **2. Client (mcp_client.py):** ```python import socket HOST = '127.0.0.1' # The server's hostname or IP address PORT = 65432 # The port used by the server def main(): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: try: s.connect((HOST, PORT)) message = input("Enter a task for the MCP: ") s.sendall(message.encode('utf-8')) data = s.recv(1024) print(f"Received: {data.decode('utf-8')}") except ConnectionRefusedError: print("Connection to the MCP server refused. Is the server running?") except Exception as e: print(f"An error occurred: {e}") if __name__ == "__main__": main() ``` **How to Run:** 1. Save the code as `mcp_server.py` and `mcp_client.py`. 2. Open a terminal or command prompt. 3. Run the server: `python mcp_server.py` 4. Open another terminal or command prompt. 5. Run the client: `python mcp_client.py` 6. The client will prompt you to enter a task. Type something and press Enter. 7. Observe the output on both the client and server consoles. **Explanation:** * **Sockets:** The `socket` library provides the foundation for network communication. We create sockets for both the server and the client. * **Server:** * `socket.socket(socket.AF_INET, socket.SOCK_STREAM)`: Creates a TCP socket (reliable, connection-oriented). * `s.bind((HOST, PORT))`: Binds the socket to a specific IP address and port. * `s.listen()`: Starts listening for incoming connections. * `s.accept()`: Accepts a connection from a client, creating a new socket (`conn`) for communication with that client. * `threading.Thread`: Creates a new thread to handle each client concurrently. This allows the server to handle multiple clients simultaneously. * `conn.recv(1024)`: Receives data from the client (up to 1024 bytes at a time). * `conn.sendall(response.encode('utf-8'))`: Sends data back to the client. * `conn.close()`: Closes the connection with the client. * **Client:** * `s.connect((HOST, PORT))`: Connects to the server at the specified IP address and port. * `s.sendall(message.encode('utf-8'))`: Sends data to the server. * `s.recv(1024)`: Receives data from the server. * **Encoding:** `encode('utf-8')` and `decode('utf-8')` are used to convert strings to bytes (for sending over the network) and bytes back to strings. UTF-8 is a common character encoding that supports a wide range of characters, including Vietnamese. * **Error Handling:** The `try...except` blocks handle potential errors like connection refused or abrupt disconnections. **Improvements and Considerations (Quan Trọng):** * **Authentication:** Implement a proper authentication mechanism (e.g., username/password, API keys, certificates) to prevent unauthorized access to the MCP. This is *crucial* for security. * **Task Queue:** Use a proper task queue (e.g., `queue.Queue` in Python, or a more robust message queue like RabbitMQ or Redis) to manage tasks efficiently. This allows the server to handle tasks asynchronously and prevent blocking. * **Resource Management:** Implement resource allocation and monitoring. The MCP should track resource usage (CPU, memory, disk I/O) and prevent clients from consuming excessive resources. * **Error Handling:** Implement more robust error handling and logging. The MCP should log all errors and exceptions to a file or database for debugging and auditing. * **Security:** Address security vulnerabilities such as injection attacks, denial-of-service attacks, and data breaches. Use secure coding practices and regularly update your software. * **Scalability:** Consider scalability requirements. If you need to handle a large number of clients, you may need to use a more scalable architecture, such as a distributed system with multiple MCP servers. * **Data Serialization:** Instead of sending plain text, use a data serialization format like JSON or Protocol Buffers to send structured data between the client and server. This makes it easier to handle complex data structures. * **Vietnamese Language Support:** * Ensure that your code uses UTF-8 encoding throughout to properly handle Vietnamese characters. * Consider translating any user-facing messages (e.g., error messages, prompts) into Vietnamese for a better user experience. * If you are storing data in a database, make sure that the database is configured to use UTF-8 encoding. **Vietnamese Translation of Key Concepts:** * **Server:** Máy chủ * **Client:** Máy khách * **Master Control Program (MCP):** Chương trình Điều khiển Chính * **Task:** Nhiệm vụ * **Resource:** Tài nguyên * **Connection:** Kết nối * **Authentication:** Xác thực * **Error:** Lỗi * **Message:** Tin nhắn * **Queue:** Hàng đợi **Example of Vietnamese Error Message:** ```python print("Lỗi: Không thể kết nối đến máy chủ MCP. Máy chủ có đang chạy không?") ``` **Important Considerations for Vietnamese Developers:** * **Character Encoding:** Always use UTF-8 encoding for all text files and data. * **Localization:** Consider localizing your application for Vietnamese users, including translating the user interface and providing support for Vietnamese date and time formats. * **Network Infrastructure:** Be aware of the network infrastructure in Vietnam, which may have different characteristics than in other countries (e.g., slower internet speeds, higher latency). This provides a basic framework. Building a real-world MCP-like system requires significantly more effort and expertise. Remember to prioritize security, scalability, and maintainability. Good luck!
NS Lookup MCP Server
Một máy chủ MCP đơn giản cung cấp chức năng lệnh nslookup.
ProofStream MCP Server
Enables AI agents to dispatch human verifiers for physical world tasks like product authentication, property inspection, and document verification, returning timestamped evidence reports.
GitLab MCP Server
Integrates GitLab with AI assistants to manage merge requests, analyze CI/CD pipelines, and create Architecture Decision Records. It enables seamless code searching, pipeline triggering, and deployment management through the Model Context Protocol.
Shepherd MCP
Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.
SpyNet
Enables AI assistants to configure and manage session-based REST and WebSocket mock servers for application development and testing. It allows for dynamic endpoint setup, request history inspection, and real-time WebSocket communication through natural language commands.
humane-proxy
It's a safety middleware that can detect and intercept self-harm and criminal intent at 3 stages. It allows developers of chat-based platforms to configure webhook notifications and store encrypted information for prior mitigation of any such cases.
Marlo MCP
Enables interaction with Marlo's maritime finance and operations platform, providing access to vessel management, voyage tracking, financial data, banking transactions, loans, compliance reporting, and operational analytics for shipping businesses.
AutoCAD MCP Server
Enables users to control AutoCAD, GstarCAD, or ZWCAD through natural language via Claude Desktop. It provides tools for drawing geometric shapes, adding text and dimensions, and managing CAD files using the Windows COM interface.
Tavily Search
Một bản triển khai máy chủ MCP (có thể là viết tắt của một thuật ngữ cụ thể trong ngữ cảnh này) tích hợp API Tìm kiếm Tavily, cung cấp các khả năng tìm kiếm được tối ưu hóa cho LLM (Mô hình Ngôn ngữ Lớn).
easy-mysql-mcp
Enables AI assistants to inspect and query a MySQL database through safe, structured tools, including schema discovery and read-only queries.
Simple MCP Server with upstream auth via local rest endpoint
Một môi trường thử nghiệm để tạo mẫu máy chủ MCP.
k8s-pilot
A lightweight, centralized control plane server that enables management of multiple Kubernetes clusters simultaneously, supporting context switching and CRUD operations on common Kubernetes resources.
mcp-remote-py
A minimal Python-based proxy that bridges local MCP STDIO clients with remote MCP SSE servers. It enables bidirectional JSON-RPC message passing between standard command-line tools and web-based remote endpoints.