Discover Awesome MCP Servers

Telegram MCP Server

Enables interaction with the Telegram Bot API via the Model Context Protocol to send, edit, and delete messages, photos, and videos. It allows Claude to manage Telegram communications and fetch bot updates through natural language commands.

server-commands-rtk

MCP server for executing shell commands with automatic RTK token reduction, persistent caching, and execution logging.

Barebones MCP Server

A minimal, dockerized template for creating HTTP-based Model Context Protocol servers. Provides a starting point with FastMCP framework integration and includes a sample cat fact tool that can be replaced with custom functionality.

Bluesky MCP Server

Enables AI agents to interact with Bluesky social network through optimized, token-efficient tools for posting, replying, searching, and managing social relationships. Features Windows-compatible implementation with context cleanup to minimize LLM token consumption.

mcp-app-ui

This MCP server provides the current server time through a basic resource and tool, following the MCP Apps quickstart.

Mimikatz MCP Server

Provides programmatic access to Mimikatz for credential extraction, Kerberos attacks, SAM/LSA dumping, and other Windows security assessment tasks through natural language.

AgentAudit

Security scanner for AI agent packages that enables AI agents to audit MCP servers and packages for vulnerabilities, prompt injection, and supply chain attacks.

MCPify

Automatically generates and runs MCP servers by scraping API documentation and using Gemini to extract endpoints and configuration. It enables users to interact with any REST API through MCP-compatible clients by simply providing a documentation URL.

messages

Enables fuzzy search and browsing of Apple Messages (iMessage/SMS) with contact resolution, filtering by sender or date, and context display through CLI, MCP, or Claude Code plugin.

MCP Calculator

A modular calculator server built with the MCP SDK that provides basic arithmetic operations (addition, subtraction, multiplication, division) with Chinese language support. Features include calculation history tracking, configuration resources, and decimal calculation prompts with comprehensive error handling.

Remote MCP Server (Authless)

Deploys a remote MCP server on Cloudflare Workers without authentication, enabling custom tools and connections to clients like Claude Desktop and Cloudflare AI Playground.

LCS CAD MCP

Exposes Pre-DCR and Auto-DCR building scrutiny workflows as AI-consumable tools, enabling AI assistants to open DXF drawings, validate layers, compute areas, run regulatory checks, and generate compliance reports via natural language.

imagedimensions-mcp

Audits images on any public web page to detect oversized images, compare natural vs rendered dimensions, and provide format breakdown, helping AI agents check image performance during development.

Crawl4AI RAG MCP Server

Provides AI agents and coding assistants with advanced web crawling and RAG capabilities, allowing them to scrape websites and leverage that knowledge through various retrieval strategies.

Peppermint MCP Server

Provides access to Peppermint Tools API for blockchain operations including smart contracts, tokens, NFTs, and more.

Sketchup Integration

Kết nối Sketchup với Claude AI thông qua Giao thức Bối cảnh Mô hình, cho phép Claude tương tác trực tiếp và điều khiển Sketchup để mô hình hóa 3D và thao tác cảnh được hỗ trợ bởi lời nhắc.

ATP Librarian MCP Server

Enforces the Agent Task Protocol (.atp.json) contract, enabling worker agents to claim, finish, and decompose tasks while maintaining a valid dependency graph.

FHIR MCP Server

A comprehensive MCP server that bridges AI applications with FHIR healthcare data systems, enabling patient data access, clinical data retrieval, and data quality assessment.

mcp-stm-montevideo

MCP server exposing Montevideo public transportation data (STM) as tools for AI assistants, enabling natural language queries about routes, stops, arrivals, and trip planning.

MCP Sigmund

Enables AI assistants to analyze personal financial data from Open Banking sources stored in PostgreSQL database. Provides educational financial analysis tools with intelligent formatting for learning about spending patterns, account balances, and transaction history.

Jokes MCP Server

A Model Context Protocol server that provides jokes on demand, allowing users to request jokes from different categories (Chuck Norris, Dad jokes, etc.) and integrate them into Microsoft Copilot Studio and Visual Studio Code.

golf-reports

Pulls golf data from Arccos, GHIN, and 18Birdies, and generates interactive HTML and PDF round reports with shot maps and stats via local MCP tools.

Git Code Review MCP

Enables AI assistants to perform code reviews by providing access to staged files, git diffs, and repository file content. It allows users to evaluate changes and context within any local git repository before committing or pushing.

MISP-mcp

Enables AI assistants to interact with MISP threat intelligence platforms through natural language, supporting event search, creation, user management, and report generation.

Name.com MCP Server

Enables management of domains and DNS records through the Name.com REST API. Users can search for available domains, check bulk availability, and configure DNS records or nameservers using natural language.

MCP Twitter/X Server

Provides integration with Twitter/X, enabling reading posts from users and creating new posts.

YouTrack MCP Server

A comprehensive Model Context Protocol server for YouTrack integration, providing extensive tools for issue tracking, project management, workflow automation, and team collaboration.

goodvat

Enables AI assistants to answer tax compliance questions (VAT, sales tax, GST) and validate EU VAT numbers in real time via the VIES registry.

API Wrapper MCP Server

Okay, I understand you want to create an MCP (Mod Control Panel) server that can interact with any API. This is a broad request, as the specific implementation depends heavily on the API you want to interact with and the features you want to expose through the MCP. However, I can provide a general outline and code snippets to get you started. **Conceptual Overview** 1. **API Interaction Layer:** This is the core of your MCP. It handles communication with the target API. You'll need to use a suitable HTTP client library (like `requests` in Python or `axios` in JavaScript) to make requests to the API endpoints. 2. **MCP Server (Web Server):** This provides the user interface (UI) and API endpoints for your MCP. Users will interact with this server to manage and control the API. You can use frameworks like Flask (Python), Express.js (Node.js), or Django (Python) to build this. 3. **Authentication and Authorization:** Crucial for security. You'll need to implement a system to verify users and control their access to different features of the MCP. 4. **Data Storage (Optional):** If you need to store user data, API keys, or other configuration information, you'll need a database (e.g., SQLite, PostgreSQL, MySQL, MongoDB). 5. **User Interface (UI):** The front-end where users interact with the MCP. This can be a simple HTML/CSS/JavaScript interface or a more complex framework like React, Angular, or Vue.js. **Example Implementation (Python with Flask)** This example demonstrates a basic MCP server using Flask that interacts with a hypothetical API. It includes authentication and a simple endpoint to make a request to the API. ```python from flask import Flask, request, jsonify, render_template, redirect, url_for from flask_login import LoginManager, UserMixin, login_required, login_user, logout_user, current_user import requests import os from werkzeug.security import generate_password_hash, check_password_hash app = Flask(__name__) app.config['SECRET_KEY'] = os.urandom(24) # Change this to a strong, random key in production! # Flask-Login setup login_manager = LoginManager() login_manager.init_app(app) login_manager.login_view = 'login' # Redirect to login page if not authenticated # Dummy user data (replace with a database in a real application) users = { "admin": {"password": generate_password_hash("password"), "id": 1} } # User class for Flask-Login class User(UserMixin): def __init__(self, id): self.id = id def get_id(self): return str(self.id) # User loader callback @login_manager.user_loader def load_user(user_id): if str(user_id) in [str(users[user]['id']) for user in users]: return User(user_id) return None # API Configuration (replace with your actual API details) API_BASE_URL = "https://api.example.com" # Replace with your API base URL API_KEY = "YOUR_API_KEY" # Replace with your API key # Routes @app.route('/') @login_required def index(): return render_template('index.html') # Create an index.html template @app.route('/api/call', methods=['GET']) @login_required def call_api(): """Example API call.""" try: # Construct the API request url = f"{API_BASE_URL}/some/endpoint" headers = {"Authorization": f"Bearer {API_KEY}"} # Example: Bearer token authentication params = {"param1": "value1"} # Example: Query parameters # Make the API request response = requests.get(url, headers=headers, params=params) response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx) # Process the API response data = response.json() return jsonify(data) except requests.exceptions.RequestException as e: return jsonify({"error": str(e)}), 500 # Handle API errors @app.route('/login', methods=['GET', 'POST']) def login(): if request.method == 'POST': username = request.form['username'] password = request.form['password'] if username in users and check_password_hash(users[username]['password'], password): user = User(users[username]['id']) login_user(user) return redirect(url_for('index')) else: return render_template('login.html', error='Invalid username or password') return render_template('login.html') # Create a login.html template @app.route('/logout') @login_required def logout(): logout_user() return redirect(url_for('login')) if __name__ == '__main__': app.run(debug=True) ``` **Explanation:** * **Flask Setup:** Initializes the Flask application and sets a secret key (important for security). * **Flask-Login:** Sets up Flask-Login for user authentication. It defines a `User` class and user loader. * **API Configuration:** Stores the API base URL and API key. **Replace these with your actual API details.** * **`/` (Index) Route:** A protected route that requires login. It renders a template (you'll need to create `index.html`). * **`/api/call` Route:** * Demonstrates how to make an API request using the `requests` library. * Constructs the API URL, headers (including authorization), and parameters. * Handles potential API errors using `try...except`. * Returns the API response as JSON. * **`/login` Route:** Handles user login. It checks the username and password against the dummy `users` dictionary. **Replace this with a database lookup in a real application.** * **`/logout` Route:** Logs the user out. **Templates (Example `login.html`)** ```html <!DOCTYPE html> <html> <head> <title>Login</title> </head> <body> <h1>Login</h1> {% if error %} <p style="color: red;">{{ error }}</p> {% endif %} <form method="post"> <label for="username">Username:</label><br> <input type="text" id="username" name="username"><br><br> <label for="password">Password:</label><br> <input type="password" id="password" name="password"><br><br> <input type="submit" value="Login"> </form> </body> </html> ``` **Key Improvements and Considerations for a Real-World MCP:** * **Database Integration:** Use a database (e.g., PostgreSQL, MySQL, MongoDB) to store user accounts, API keys, and other configuration data. Use an ORM like SQLAlchemy (Python) or Mongoose (Node.js) to interact with the database. * **Robust Authentication:** Implement a more secure authentication system, such as using JWT (JSON Web Tokens) or OAuth 2.0. Consider using a library like `Flask-Security` or `Flask-Praetorian` to simplify authentication. * **Input Validation:** Thoroughly validate all user input to prevent security vulnerabilities like SQL injection and cross-site scripting (XSS). * **Error Handling:** Implement comprehensive error handling to gracefully handle API errors, database errors, and other unexpected situations. Log errors for debugging. * **Rate Limiting:** Implement rate limiting to prevent abuse of your MCP and the underlying API. * **Asynchronous Tasks:** For long-running API operations, use asynchronous tasks (e.g., Celery with Redis) to avoid blocking the main server thread. * **Configuration Management:** Use a configuration file (e.g., YAML, JSON) to store API keys, database connection strings, and other configuration settings. Avoid hardcoding sensitive information in your code. * **User Interface (UI):** Develop a user-friendly UI using HTML, CSS, and JavaScript. Consider using a front-end framework like React, Angular, or Vue.js to build a more complex and interactive UI. * **API Abstraction:** Create an abstraction layer between your MCP and the target API. This will make it easier to switch to a different API in the future. * **Logging:** Implement detailed logging to track user activity, API requests, and errors. Use a logging library like `logging` (Python) or `winston` (Node.js). * **Security Audits:** Regularly perform security audits to identify and fix potential vulnerabilities. **Steps to Adapt This to Your Specific API:** 1. **Replace Placeholder Values:** Update `API_BASE_URL` and `API_KEY` with the correct values for your target API. 2. **Understand the API:** Carefully study the API documentation to understand the available endpoints, request parameters, authentication methods, and response formats. 3. **Implement API Calls:** Modify the `call_api` function to make the specific API calls you need. Adjust the URL, headers, parameters, and data processing logic accordingly. 4. **Create UI Elements:** Design and implement UI elements (e.g., forms, buttons, tables) to allow users to interact with the API through your MCP. 5. **Handle API Responses:** Process the API responses and display the results to the user in a clear and informative way. 6. **Implement Error Handling:** Add error handling to gracefully handle API errors and display informative error messages to the user. 7. **Add Authentication:** Implement a secure authentication system to protect your MCP and the underlying API. 8. **Deploy:** Deploy your MCP to a suitable hosting environment (e.g., Heroku, AWS, Google Cloud). **Vietnamese Translation of Key Concepts:** * **MCP (Mod Control Panel):** Bảng điều khiển sửa đổi (or Bảng điều khiển điều khiển) * **API (Application Programming Interface):** Giao diện lập trình ứng dụng * **Server:** Máy chủ * **Authentication:** Xác thực * **Authorization:** Phân quyền * **Database:** Cơ sở dữ liệu * **User Interface (UI):** Giao diện người dùng * **Endpoint:** Điểm cuối (API) * **Request:** Yêu cầu * **Response:** Phản hồi * **API Key:** Khóa API * **Login:** Đăng nhập * **Logout:** Đăng xuất This comprehensive guide should give you a solid foundation for building your MCP server. Remember to adapt the code and concepts to your specific API and requirements. Good luck!

syplugin-anMCPServer

A Model Context Protocol server plugin for SiYuan note-taking application that enables searching documents, retrieving content, and writing to notes through an HTTP-based interface.