Discover Awesome MCP Servers

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).

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.

astro-airflow-mcp

An MCP server that enables AI assistants to interact with Apache Airflow's REST API for DAG management, task monitoring, and system diagnostics. It provides comprehensive tools for triggering workflows, retrieving logs, and inspecting system health across Airflow 2.x and 3.x versions.

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!

Simple Voice MCP Server

Enables text-to-speech playback with multiple Japanese character voices using VLC, supporting simultaneous audio playback and custom pronunciation dictionaries for English words.

rust-faf-mcp RMCP

Persistent project context in Rust. 8 MCP tools via rmcp SDK — parse, validate, score, compress, discover, and token analysis. Single binary, zero config. IANA-registered format (application/vnd.faf+yaml). One file, every AI platform.

OpenAccess MCP

Enables secure remote access operations through SSH, SFTP, rsync, VPN, and tunneling with enterprise-grade policy enforcement and audit logging. Provides AI assistants with secure, policy-driven access to remote systems while maintaining comprehensive audit trails and zero-trust security.

TreeBeam MCP Server

Enables AI assistants to interact with the TreeBeam financial management and accounting platform. Users can list organizations and projects using secure OAuth 2.0 authentication integrated directly into their AI conversation.

custom_mcp_server

Building custom MCP server

epsteinexposed-mcp

MCP to explore the EpsteinExposed API through the epsteinexposed pip api wrapper.

Gemini MCP

An AI-powered Model Context Protocol server for Claude Code that provides code intelligence tools including codebase analysis, task management, component generation, and deployment configuration.

MedGemma Vertex

MCP server that routes medical questions and images to MedGemma models hosted on Vertex AI, enabling interaction with text-only and multimodal medical AI systems.

WhatsApp Business API MCP Server

An MCP (Multi-Agent Conversation Protocol) Server that enables interaction with the WhatsApp Business API, allowing agents to send messages, manage media, and perform other WhatsApp business operations through natural language.

MOIDVK

A comprehensive Model Context Protocol (MCP) server that provides 37+ intelligent development tools across JavaScript/TypeScript, Rust, and Python with security-first design and high-performance features.

Basic MCP Application

Một ứng dụng đơn giản minh họa tích hợp Giao thức Ngữ cảnh Mô hình (MCP) với FastAPI và Streamlit, cho phép người dùng tương tác với LLM thông qua một giao diện rõ ràng.

aws-mcp-cloud-dev

AI-powered cloud development with AWS MCP Servers

mcp-cloudflare

Slim Cloudflare MCP Server — 42 tools for managing DNS, zones, tunnels, WAF, Zero Trust, and security via Cloudflare API v4. Multi-zone support. No SSH, no shell, API-only with 3 runtime dependencies. AGPL-3.0 + Commercial dual-licensed.

FamilySearch MCP Server

Một máy chủ Giao thức Bối cảnh Mô hình (Model Context Protocol server) cho phép các công cụ AI như Claude hoặc Cursor tương tác trực tiếp với dữ liệu lịch sử gia đình của FamilySearch, bao gồm tìm kiếm hồ sơ cá nhân, xem thông tin chi tiết và khám phá tổ tiên và hậu duệ.

Red Team MCP

A multi-agent collaboration platform that provides access to over 1,500 models from 68 providers via the Model Context Protocol. It enables users to assemble and coordinate specialized AI teams using advanced orchestration modes like swarm, debate, and hierarchical workflows.

Garak-MCP

Máy chủ MCP cho Trình quét lỗ hổng Garak LLM https://github.com/EdenYavin/Garak-MCP/blob/main/README.md

SpiderFoot MCP Server

Enables interaction with SpiderFoot OSINT reconnaissance tools through MCP, allowing users to manage scans, retrieve modules and event types, access scan data, and export results. Supports both starting new scans and analyzing existing reconnaissance data through natural language.

Claude Runner MCP

An MCP server for scheduling and executing Claude Code CLI tasks via cron expressions, featuring a web dashboard and webhook support. It enables users to dynamically create custom MCP servers, manage recurring AI jobs, and track execution history with token and cost analytics.