Discover Awesome MCP Servers

MCP-123

A lightweight implementation that provides the simplest way to set up an MCP server and client, requiring just two lines of code to create a fully functional system.

Freshdesk MCP Server

Enables interaction with Freshdesk API v2 to manage support tickets, contacts, agents, companies, and conversations with built-in authentication, rate limiting, and error handling.

useblip/email

MCP server for disposable email — create inboxes, receive emails, and extract OTP codes. Let your AI agent sign up for services, wait for verification emails, and extract codes autonomously.

MCP Server Demo

A minimal WebSocket-based MCP server implementation that enables modern tool integrations with VSCode, Claude, and other applications.

MCP Router

Automatically selects the optimal LLM model for each task in Cursor IDE by analyzing query complexity, task type, and applying customizable routing strategies across 17 different AI models.

MotaWord MCP Server

This MCP gives you full control over your translation projects from start to finish. You can log in anytime to see what stage your project is in — whether it’s being translated, reviewed, or completed.

MediaWiki Syntax MCP Server

This MCP server provides complete MediaWiki markup syntax documentation by dynamically fetching and consolidating information from official MediaWiki help pages. It enables LLMs to access up-to-date and comprehensive MediaWiki syntax information.

Overview

Lần đầu thử máy chủ MCP.

Jokes MCP Server

A Model Context Protocol server that enables Microsoft Copilot Studio to fetch jokes from various sources including Chuck Norris jokes, Dad jokes, and Yo Mama jokes.

MCP demo (DeepSeek as Client's LLM)

Okay, I understand. You want instructions on how to run a Minimal Communication Protocol (MCP) client and server demo using the DeepSeek API. Unfortunately, I need a little more information to give you a precise and helpful answer. Here's why, and what I need to know: **Why I need more information:** * **"MCP" is very generic:** "Minimal Communication Protocol" could refer to many different things. It's not a standardized protocol like HTTP or TCP. It's likely a custom protocol you or someone else has defined. * **DeepSeek API's Role:** The DeepSeek API is primarily known for its large language models (LLMs). It's not immediately clear how it fits into a *communication protocol* demo. Are you intending to use the DeepSeek API to: * **Generate messages for the MCP?** (e.g., the server uses DeepSeek to create responses based on client requests) * **Analyze messages sent over the MCP?** (e.g., the server uses DeepSeek to understand the intent of client requests) * **Something else entirely?** * **Existing Code/Setup:** Do you already have: * MCP client and server code (even if it's basic)? * A DeepSeek API key? * A programming language preference (Python, Node.js, etc.)? **Here's what I need you to tell me so I can provide a useful answer:** 1. **Describe the MCP:** * What is the purpose of this MCP? What kind of data will be exchanged? * What is the message format (e.g., text-based, binary, JSON)? If text-based, what's the structure? * What are the basic commands or message types? 2. **Explain how you want to use the DeepSeek API:** * Specifically, what role will the DeepSeek API play in the client/server interaction? Give a concrete example. 3. **Programming Language:** * What programming language are you using (e.g., Python, Node.js, Go, Java)? 4. **Existing Code (if any):** * Please share any code you already have for the MCP client, server, or DeepSeek API integration. Even snippets are helpful. 5. **DeepSeek API Key:** * Do you have a DeepSeek API key? (You don't need to share the key itself, just confirm you have one). **Example Scenario (and how I would answer *if* this were your scenario):** Let's *imagine* you want to build a simple "Echo Server" MCP where: * **MCP:** * Clients send text messages to the server. * The server *echoes* the message back to the client, but *enhanced* by the DeepSeek API. * Message format: Plain text. * Command: Just send text; no specific commands. * **DeepSeek API:** * The server uses the DeepSeek API to add a humorous or creative "spin" to the echoed message. For example, if the client sends "Hello", the server might respond with "Hello! As a large language model, I'm contractually obligated to say: Have a fantastic day!". * **Language:** Python * **I have a DeepSeek API key.** **Then, I could provide a Python example like this:** ```python import socket import deepseek_client # Assuming you have a DeepSeek client library # Replace with your DeepSeek API key DEEPSEEK_API_KEY = "YOUR_DEEPSEEK_API_KEY" # MCP Server settings HOST = '127.0.0.1' # Standard loopback interface address (localhost) PORT = 65432 # Port to listen on (non-privileged ports are > 1023) def enhance_with_deepseek(message): """Uses the DeepSeek API to enhance the message.""" try: client = deepseek_client.DeepSeekClient(DEEPSEEK_API_KEY) # Replace with your actual client initialization prompt = f"Enhance the following message with a humorous or creative twist: '{message}'" response = client.generate_text(prompt) # Replace with the correct method call return response.text # Assuming the response has a 'text' attribute except Exception as e: print(f"Error using DeepSeek API: {e}") return f"Error: Could not enhance message. Original: {message}" # Fallback def run_server(): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() print(f"Server listening on {HOST}:{PORT}") conn, addr = s.accept() with conn: print(f"Connected by {addr}") while True: data = conn.recv(1024) if not data: break message = data.decode('utf-8') enhanced_message = enhance_with_deepseek(message) conn.sendall(enhanced_message.encode('utf-8')) def run_client(): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) message = input("Enter message to send: ") s.sendall(message.encode('utf-8')) data = s.recv(1024) print(f"Received: {data.decode('utf-8')}") if __name__ == "__main__": import threading server_thread = threading.Thread(target=run_server) server_thread.daemon = True # Allow the main thread to exit even if the server is running server_thread.start() run_client() ``` **Important Notes about the Example:** * **`deepseek_client`:** This is a placeholder. You'll need to install the appropriate DeepSeek API client library for Python (if one exists; otherwise, you'll need to use `requests` or a similar library to make HTTP calls to the DeepSeek API). You'll also need to adapt the `deepseek_client.DeepSeekClient()` and `client.generate_text()` calls to match the actual API usage. Refer to the DeepSeek API documentation for details. * **Error Handling:** The example includes basic error handling for the DeepSeek API call. You should add more robust error handling in a real application. * **Threading:** The server runs in a separate thread so the client and server can run concurrently on the same machine for testing. * **Replace `YOUR_DEEPSEEK_API_KEY`:** You *must* replace this with your actual DeepSeek API key. * **Install `socket`:** This is a built-in Python library, so no installation is needed. **How to Run the Example (after you've adapted it):** 1. **Save:** Save the code as a Python file (e.g., `mcp_deepseek_demo.py`). 2. **Install DeepSeek Client (if applicable):** `pip install deepseek-client` (or whatever the correct package name is). 3. **Run:** Execute the script from your terminal: `python mcp_deepseek_demo.py` 4. **Enter a message:** The client will prompt you to enter a message. Type something and press Enter. 5. **See the response:** The client will display the enhanced message received from the server. **In summary, please provide the details I requested above so I can give you a much more specific and helpful answer.**

Skills MCP Server

Exposes 1,334 skills as global MCP tools across Claude Desktop, VSCode, and Cursor, automatically discovering and categorizing skills from a local directory into 18 categories with semantic search capabilities.

Apple Doc MCP

A Model Context Protocol server that provides AI coding assistants with direct access to Apple's Developer Documentation, enabling seamless lookup of frameworks, symbols, and detailed API references.

BRAINS OS - version MCP

Một triển khai MCP (Multi-Cloud Platform) không máy chủ sử dụng SST, React và AWS.

MCPizza

An MCP server that allows AI assistants to order Domino's Pizza through an unofficial API, with features for store location, menu browsing, and order management.

Local FAISS MCP Server

Provides local vector database functionality using FAISS for document ingestion, semantic search, and Retrieval-Augmented Generation (RAG) applications with persistent storage and customizable embedding models.

MCP MySQL Server

Enables AI assistants to safely query MySQL databases with read-only access by default, supporting table listing, structure inspection, and SQL queries with optional write operation control.

ServiceDesk Plus MCP Server

A Model Context Protocol server for integrating with ServiceDesk Plus On-Premise that provides comprehensive CMDB functionality, allowing users to manage tickets, assets, software licenses, contracts, vendors, and administrative settings through natural language.

Swagger to MCP

Automatically converts Swagger/OpenAPI specifications into dynamic MCP tools, enabling interaction with any REST API through natural language by loading specs from local files or URLs.

Canvas LMS MCP Server

Connects Claude to Canvas LMS accounts, enabling natural language queries about courses, assignments, grades, and files. Supports content search, file downloads, syllabus retrieval, and bulk course exports via 13 integrated tools.

claude-peers

Enables discovery and instant communication between multiple local Claude Code instances running across different projects. It allows agents to list active peers, share work summaries, and send messages through a local broker daemon.

Lotus MCP

Enables creation of reusable browser automation skills through demonstration by recording user actions in a browser while narrating, then converting those workflows into executable skills that can be invoked through natural language.

mcp-shell

Give hands to AI. MCP server to run shell commands securely, auditably, and on demand.

Cloudflare Control

Enables AI assistants to manage Cloudflare infrastructure including DNS records, cache purging, SSL settings, Workers, and analytics through the Cloudflare API. Eliminates dashboard context-switching by allowing natural language control of domain management and infrastructure operations.

Layout Detector MCP

Analyzes webpage screenshots to extract precise layout information by locating image assets and calculating spatial relationships, enabling AI assistants to accurately recreate layouts with proper semantic structure using computer vision.

JMeter MCP Server

Enables the execution and analysis of JMeter performance tests through MCP-compatible clients. It provides tools for running tests in non-GUI mode, identifying performance bottlenecks, and generating comprehensive insights and visualizations from result files.

s-GitHubTestRepo-HJA3

created from MCP server demo

Open Brain MCP Server

A personal semantic knowledge base that enables storing, searching, and retrieving memories and work history using natural language. It features vector-based search, tool discovery via a registry, and indexing of Cursor agent transcripts using Supabase or Postgres.

Multi-Capability Proxy Server

A Flask-based server that hosts multiple tools, each exposing functionalities by calling external REST APIs through a unified interface.

Fed Speech MCP

Retrieves, parses, and analyzes speeches and testimonies from Federal Reserve officers, enabling searches by speaker, topic, and keyword with automatic RSS feed discovery and intelligent relevance scoring.