Discover Awesome MCP Servers

agentguard

Enables scanning of AI agent code for security vulnerabilities such as prompt injection, tool abuse, and data exfiltration, directly from MCP-compatible clients like Claude Code.

mcp-cli-catalog

An MCP server that publishes CLI tools on your machine for discoverability by LLMs

minesweeper-mcp

A stdio-based MCP server that enables users to play and manage Minesweeper games through a Rails 8 REST API. It provides tools to start games, track states, and perform actions like opening cells and flagging mines.

temporal-mcp-server

Enables AI assistants to observe and manage Temporal workflows, including listing, starting, signaling, resetting, terminating, querying, and retrieving history, with support for wait_for_activity and webhook utilities.

trae-memory

智能记忆系统，为TRAE IDE提供自动对话记录、上下文恢复和任务管理功能。

Respira for WordPress

MCP server for AI-assisted WordPress editing across 12 page builders. 172 tools for content management, page builder editing, WooCommerce, SEO analysis, accessibility scanning, and site intelligence. Edits native builder formats (Elementor, Bricks, Divi, Gutenberg, Beaver Builder, and 7 more) with duplicate-before-edit safety, optimistic locking, and surgical element-level operations

COMSOL MCP Server

Enables AI agents to automate COMSOL Multiphysics simulations, including model management, geometry building, physics configuration, meshing, solving, and results visualization through the MCP protocol.

Medikode Medical Coding MCP Server

Enables AI assistants to access Medikode's medical coding platform for validating CPT/ICD-10 codes, performing chart quality assurance, parsing EOBs, calculating RAF scores, and extracting HCC codes from clinical documentation.

MCP Client-Server Sandbox for LLM Augmentation

Banco de pruebas completo para aumentar la inferencia de LLM (local o en la nube) con MCP Cliente-Servidor. Entorno de pruebas de baja fricción para la validación del servidor MCP y la evaluación agentica.

nj-realtor-mcp

A production-grade MCP server enabling Claude to perform comprehensive NJ real estate workflows including property search, valuation, neighborhood intelligence, investment analysis, and agent tools via 20 tools and 15+ data sources.

MCP Tailwind Gemini Server

Advanced Model Context Protocol server that integrates Gemini AI with Tailwind CSS, providing intelligent component generation, class optimization, and cross-platform design assistance across major development environments.

Skyvern MCP

Skyvern MCP server lets AI agents control a real browser to navigate websites, fill forms, authenticate, and extract structured data. Supports multi-step automation workflows via natural language.

code-analyze-mcp

Standalone MCP server for code structure analysis using tree-sitter. Directory trees, symbol definitions, and call graphs without reading raw source files. Supports Rust, Python, Go, Java, TypeScript, Fortran, JavaScript, C/C++, and C#. Benchmarked up to 68% fewer tokens vs native tools.

Behance MCP Server

A powerful Model Context Protocol (MCP) server for scraping Behance.net. Extract projects, user profiles, images, and job listings from Behance's creative community without any API keys or subscriptions.

VA-MCP

An MCP server for checking OWASP Top 10 vulnerabilities during API development testing. It analyzes API information and returns security assessment results to help developers identify potential security issues.

OpenTelemetry MCP Server

Enables AI agents to query Prometheus metrics and Loki logs for intelligent alert investigation and troubleshooting. Provides service discovery, metric querying, log searching, and correlation tools to help identify root causes of issues.

aws-blackbelt-mcp-server

A Model Context Protocol (MCP) server that enables searching AWS Black Belt Online Seminars and retrieving their transcripts.

Quack MCP Server

A continuous integration server that automates Python code analysis, providing linting and static type checking tools for quality assurance.

Email Sender MCP Server

Enables sending emails through SMTP with support for multiple recipients, attachments, CC/BCC, and both plain text and HTML formats. Includes preset configurations for common email providers like Gmail, QQ, Outlook, and 163.

TimeLiner MCP Server

An MCP server for controlling the TimeLiner project management system, enabling AI clients to manage projects, tasks, members, and more via natural language.

ytmcp

Enables AI assistants to fetch YouTube video transcripts with precise timestamps, multi-language support, and time-range filtering.

Model Context Protocol (MCP) MSPaint App Automation

Okay, this is a more complex request involving several parts: a server, a client, math problem solving, and integration with MSPaint. I'll provide a conceptual outline and Python code snippets to get you started. Keep in mind that this is a simplified example, and a production-ready solution would require more robust error handling, security, and potentially a more sophisticated drawing mechanism. **Conceptual Outline** 1. **Server (Python):** * Listens for client connections. * Receives math problems (as strings). * Solves the problem (using `eval` or a safer alternative like `ast.literal_eval` for simple expressions, or a dedicated math library for more complex problems). * Generates a solution string (including steps, if possible). * Sends the solution string back to the client. 2. **Client (Python):** * Connects to the server. * Prompts the user for a math problem. * Sends the problem to the server. * Receives the solution from the server. * Generates a simple image of the solution using a library like Pillow (PIL). * Opens the image in MSPaint using `os.system` or `subprocess`. **Code Snippets (Python)** **Server (server.py):** ```python import socket import threading import ast # Safer alternative to eval for simple expressions 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): print(f"Connected by {addr}") with conn: while True: data = conn.recv(1024) if not data: break problem = data.decode() print(f"Received problem: {problem}") try: # Safely evaluate the expression (use ast.literal_eval for simple expressions) solution = str(ast.literal_eval(problem)) # VERY IMPORTANT: See security notes below solution_string = f"Problem: {problem}\nSolution: {solution}" except (SyntaxError, NameError, TypeError) as e: solution_string = f"Error: Invalid problem format or unsupported operation: {e}" except Exception as e: solution_string = f"Error: An unexpected error occurred: {e}" conn.sendall(solution_string.encode()) def main(): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() print(f"Server listening on {HOST}:{PORT}") while True: conn, addr = s.accept() thread = threading.Thread(target=handle_client, args=(conn, addr)) thread.start() if __name__ == "__main__": main() ``` **Client (client.py):** ```python import socket import os import subprocess from PIL import Image, ImageDraw, ImageFont # Install Pillow: pip install Pillow HOST = '127.0.0.1' # The server's hostname or IP address PORT = 65432 # The port used by the server def create_image(text, filename="solution.png"): """Creates a simple image with the given text.""" image_width = 800 image_height = 600 img = Image.new('RGB', (image_width, image_height), color='white') d = ImageDraw.Draw(img) try: font = ImageFont.truetype("arial.ttf", size=24) # You might need to adjust the font path except IOError: font = ImageFont.load_default() # Use a default font if Arial is not found d.text((50, 50), text, fill='black', font=font) img.save(filename) return filename def open_mspaint(image_path): """Opens the image in MSPaint.""" try: # Use subprocess for better control and error handling subprocess.run(["mspaint", image_path], check=True) except FileNotFoundError: print("MSPaint not found. Make sure it's in your system's PATH.") except subprocess.CalledProcessError as e: print(f"Error opening MSPaint: {e}") def main(): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) problem = input("Enter a math problem: ") s.sendall(problem.encode()) data = s.recv(4096) # Increased buffer size solution = data.decode() print(f"Received solution: {solution}") image_file = create_image(solution) open_mspaint(image_file) if __name__ == "__main__": main() ``` **How to Run:** 1. **Install Pillow:** `pip install Pillow` 2. **Save:** Save the server code as `server.py` and the client code as `client.py`. 3. **Run the Server:** Open a terminal and run `python server.py`. 4. **Run the Client:** Open another terminal and run `python client.py`. 5. **Enter a Problem:** The client will prompt you for a math problem. Enter something like `2 + 2` or `3 * 5`. 6. **MSPaint Opens:** MSPaint should open with an image containing the problem and the solution. **Important Considerations and Improvements:** * **Security (VERY IMPORTANT):** The use of `eval` (or even `ast.literal_eval` with user-provided input) is *extremely dangerous* in a production environment. It allows arbitrary code execution if the input is not carefully sanitized. **Never use `eval` or `ast.literal_eval` with untrusted input.** Instead, use a dedicated math parsing library like `sympy` or implement a safe expression evaluator. For example, you could create a function that only allows specific operators and numbers. The example above uses `ast.literal_eval` which is safer than `eval` but still has risks if the input is not carefully controlled. It's suitable for *very* simple expressions. * **Error Handling:** The code includes basic error handling, but you should add more robust error handling, especially around network connections and file operations. * **Solution Steps:** Generating detailed solution steps is a complex task. Libraries like `sympy` can help with this, but it requires more advanced programming. * **Drawing in MSPaint:** The current code creates a simple image and opens it in MSPaint. To draw directly in MSPaint, you would need to use the Windows API (using libraries like `pywin32`) to control MSPaint's drawing functions. This is significantly more complex. Consider using a more powerful drawing library like `matplotlib` or `seaborn` if you need more sophisticated graphics. * **Multi-threading:** The server uses threads to handle multiple clients concurrently. This is a good practice for scalability. * **Image Font:** The client code tries to use Arial font. If it's not available, it falls back to a default font. You might need to adjust the font path depending on your system. * **MSPaint Location:** The `open_mspaint` function assumes that MSPaint is in your system's PATH. If it's not, you'll need to provide the full path to `mspaint.exe`. * **Protocol:** This example uses a very simple text-based protocol. For more complex interactions, consider using a more structured protocol like JSON or Protocol Buffers. * **Dependencies:** Make sure you have the necessary libraries installed (`Pillow`). This comprehensive response provides a solid foundation for building your MCP server/client application. Remember to prioritize security and error handling as you develop your project further. Good luck!

readypermit-mcp

AI-powered property intelligence for instant zoning analysis, buildability assessments, ADU eligibility, flood risk, and development feasibility reports for any US address.

IoT Device Management MCP Server

Enables registration, monitoring, and control of IoT devices via AI agents, with local storage and no cloud API key required.

jira-minimal-mcp

Minimal MCP server for Jira with configurable tools to reduce token usage, starting from ~150 tokens for basic issue retrieval.

Purple Flea Wallet

Non-custodial HD wallet API for AI agents. Generate wallets on 6 chains (ETH, Base, SOL, BTC, TRX, XMR), check balances, send crypto, and swap cross-chain via Wagyu aggregator. 10% referral commissions.

Remote MCP Server Authless

A Cloudflare Workers-based Model Context Protocol server without authentication requirements, allowing users to deploy and customize AI tools that can be accessed from Claude Desktop or Cloudflare AI Playground.

MCP Memory

An MCP server that enables clients like Cursor, Claude, and Windsurf to remember user information and preferences across conversations using vector search technology.

Seq MCP Server

MCP server for querying structured logs from Datalust Seq, providing tools to search logs, retrieve recent errors, fetch events, and check health.

kd-mcp

Controls kd.exe for KDNET kernel debugging on Windows, often paired with winrm-mcp for guest VM setup over WinRM.