Discover Awesome MCP Servers

MCP Demo Server

A minimal fastmcp demonstration server that provides a simple addition tool through the MCP protocol, supporting deployment via Docker with multiple transport modes.

RealTest MCP Server

Provides structured access to RealTest backtesting documentation and example scripts to help LLM agents generate accurate RealScript code. It offers tools for semantic search, authoritative function references, and verified script retrieval to prevent hallucinations.

Applitools MCP Server

Enables AI assistants to set up, manage, and analyze visual tests using Applitools Eyes within Playwright JavaScript and TypeScript projects. It supports adding visual checkpoints, configuring cross-browser testing via Ultrafast Grid, and retrieving structured test results.

Somnia MCP Server

Enables AI agents to interact with the Somnia blockchain network, including documentation search, blockchain queries, wallet management, cryptographic signing, and on-chain operations.

Cars MCP Server

Basic MCP server example with Spring AI

FFmpeg MCP

Enables video and audio processing through FFmpeg, supporting format conversion, compression, trimming, audio extraction, frame extraction, video merging, and subtitle burning through natural language commands.

MCP Weather Server

Enables users to retrieve current weather alerts for US states and detailed weather forecasts by geographic coordinates using the US National Weather Service API. Built with Node.js and TypeScript following Model Context Protocol standards for seamless LLM integration.

fastf1-mcp-server

MCP server for Formula 1 data via the FastF1 library. Ask Claude (or any MCP-compatible client) about race results, lap times, telemetry, standings, pit stops, and qualifying — with historical data back to 1950 via the Ergast API.

mcp_server

날씨 MCP (Message Passing Communication) 서버 구현으로, Cursor와 같은 클라이언트 IDE에서 호출할 수 있습니다. (이 번역은 "An implementation of weather mcp server that can be called by a clinet IDE like cursor."를 가장 정확하게 전달하는 번역입니다. 만약 더 구체적인 의미를 담고 싶다면, 예를 들어 "날씨 정보를 제공하는 MCP 서버 구현"과 같이 더 자세한 정보를 제공해주시면 더 정확한 번역이 가능합니다.)

Model Context Protocol (MCP) + Spring Boot Integration

새로운 MCP 서버 기능을 Spring Boot를 사용하여 테스트 중.

Expense Tracker MCP Server

Enables AI assistants like Claude to manage personal expenses locally using SQLite. Supports adding, categorizing, summarizing expenses, setting budgets, and exporting data without cloud services.

Model Context Protocol (MCP) MSPaint App Automation

I can provide you with a conceptual outline and code snippets to illustrate how you might approach building a simple Model Context Protocol (MCP) server-client system for solving math problems and displaying the solution in MSPaint. However, directly controlling MSPaint programmatically can be tricky and might require external libraries or workarounds. This example focuses on the core MCP communication and a simplified way to visualize the solution (e.g., saving an image that can be opened in MSPaint). **Conceptual Outline:** 1. **MCP Server (Python):** * Listens for incoming client requests. * Receives a math problem (e.g., as a string). * Solves the problem (using libraries like `sympy` or `numpy`). * Generates a visual representation of the solution (e.g., using `matplotlib` to create a graph or equation). * Saves the visual representation as an image file (e.g., PNG). * Sends a response to the client, indicating success and the path to the image file. 2. **MCP Client (Python):** * Sends a math problem to the server. * Receives the server's response (success/failure and image path). * Opens the image file in MSPaint (using `os.startfile` on Windows or similar methods on other platforms). **Code Snippets (Python):** **MCP Server (server.py):** ```python import socket import sympy import matplotlib.pyplot as plt import io import base64 from PIL import Image import os HOST = '127.0.0.1' # Standard loopback interface address (localhost) PORT = 65432 # Port to listen on (non-privileged ports are > 1023) def solve_and_visualize(problem): """Solves the math problem and generates a visual representation.""" try: # Solve the problem using sympy x = sympy.symbols('x') equation = sympy.sympify(problem) solution = sympy.solve(equation, x) # Create a plot (example: plotting the equation) x_vals = range(-10, 11) y_vals = [sympy.lambdify(x, equation)(val) for val in x_vals] plt.plot(x_vals, y_vals) plt.xlabel("x") plt.ylabel("y") plt.title(f"Solution to: {problem}") plt.grid(True) # Save the plot to a file image_path = "solution.png" plt.savefig(image_path) plt.close() # Close the plot to free memory return True, image_path except Exception as e: print(f"Error solving/visualizing: {e}") return False, str(e) 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 problem = data.decode() print(f"Received problem: {problem}") success, result = solve_and_visualize(problem) if success: response = f"Success: {result}".encode() else: response = f"Error: {result}".encode() conn.sendall(response) ``` **MCP Client (client.py):** ```python import socket import os import platform HOST = '127.0.0.1' # The server's hostname or IP address PORT = 65432 # The port used by the server def open_with_mspaint(image_path): """Opens the image in MSPaint.""" try: if platform.system() == "Windows": os.startfile(image_path) # Windows elif platform.system() == "Darwin": # macOS os.system(f"open -a PaintBrush {image_path}") # Requires Paintbrush app else: # Linux (requires a suitable image viewer) os.system(f"xdg-open {image_path}") except Exception as e: print(f"Error opening MSPaint: {e}") with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) problem = input("Enter a math problem (e.g., x**2 - 4 = 0): ") s.sendall(problem.encode()) data = s.recv(1024) response = data.decode() print(f"Received: {response}") if "Success:" in response: image_path = response.split(": ")[1] open_with_mspaint(image_path) else: print("Problem solving failed.") ``` **Explanation and Improvements:** * **Libraries:** The code uses `socket` for network communication, `sympy` for symbolic math, `matplotlib` for plotting, and `os` for file operations and opening MSPaint. Install these using `pip install sympy matplotlib Pillow`. * **Error Handling:** Includes basic `try...except` blocks for error handling. More robust error handling is recommended. * **Visualization:** The `solve_and_visualize` function now creates a simple plot of the equation. You can customize this to display the solution in a more informative way (e.g., plotting the roots of the equation). It saves the plot as a PNG file. * **Image Handling:** The server saves the plot as a PNG file. The client receives the file path and attempts to open it with MSPaint. * **Platform Compatibility:** The `open_with_mspaint` function attempts to open the image using platform-specific commands. This is a basic approach; you might need to adjust it based on the user's operating system and available image viewers. On macOS, it uses `Paintbrush` which is a free MSPaint alternative. * **MCP Communication:** The code uses a simple text-based protocol. The server sends "Success: <image\_path>" or "Error: <error\_message>". You could use a more structured format like JSON for more complex data. * **Security:** This is a very basic example and lacks security features. In a real-world application, you would need to consider security implications, especially if you are accepting arbitrary math problems from clients. Sanitize inputs to prevent code injection. * **MSPaint Automation:** Directly controlling MSPaint programmatically is difficult. The `os.startfile` (Windows) or `os.system` (macOS/Linux) approach simply opens the image in MSPaint (or the default image viewer). For more advanced control, you might need to explore libraries like `pywinauto` (Windows) or platform-specific APIs. However, these can be complex. * **Threading/Asynchronous Operations:** For a production server, you would want to use threading or asynchronous operations to handle multiple client requests concurrently. **How to Run:** 1. **Save:** Save the server code as `server.py` and the client code as `client.py`. 2. **Install Libraries:** `pip install sympy matplotlib Pillow` 3. **Run the Server:** `python server.py` 4. **Run the Client:** `python client.py` 5. **Enter a Problem:** When prompted by the client, enter a math problem (e.g., `x**2 - 4 = 0`). 6. **View the Solution:** The client should receive a response from the server, and MSPaint (or the default image viewer) should open, displaying the solution. **Important Considerations:** * **MSPaint Automation Complexity:** Directly controlling MSPaint is challenging. The provided code opens the image in MSPaint, but you can't directly draw on it or manipulate it programmatically without significant effort and platform-specific code. * **Security:** Be very careful about accepting arbitrary math problems from clients, as this could pose a security risk. Sanitize inputs thoroughly. * **Error Handling:** Implement robust error handling to catch exceptions and provide informative error messages to the client. * **Scalability:** For a production system, consider using a more scalable architecture with threading or asynchronous operations to handle multiple clients concurrently. * **Alternative Visualization:** If you don't need to use MSPaint specifically, consider using other libraries like `PIL` (Pillow) to create and manipulate images directly in your Python code. This would give you more control over the image generation process. This revised response provides a more complete and practical example, along with important considerations for building a real-world MCP server-client system. Remember to adapt the code to your specific needs and environment.

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.

Databricks MCP Server

A Model Context Protocol server that enables AI assistants to interact with Databricks workspaces, allowing them to browse Unity Catalog, query metadata, sample data, and execute SQL queries.

MCP Server with Azure Communication Services Email

Azure Communication Services - 이메일 MCP

DrissionPage MCP Browser Automation

Provides browser automation and web scraping capabilities including page navigation, form filling, data extraction, and intelligent conversion of web pages to Markdown format.

i1n

Localization as code — push, pull, translate, and extract strings from code with AI. 7 MCP tools for type-safe i18n across 182 languages.

Memory-IA MCP Server

Enables AI agents with persistent memory using SQLite and local LLM models through Ollama integration. Provides chat with context retention and multi-client support across VS Code, Gemini-CLI, and terminal interfaces.

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.

React USWDS MCP Server

Indexes the locally-installed @trussworks/react-uswds package and helps code assistants discover components, inspect props, generate correct imports and usage snippets, and suggest appropriate components for UI use cases.

Canteen MCP

A Model Context Protocol server that provides structured access to canteen lunch menus for specific dates through a simple API integration.

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.

Anki MCP Server

Enables AI assistants to manage Anki flashcard decks and cards through natural language, supporting deck creation, card additions (basic and cloze types), and review queue management.

Freedcamp MCP Server

A Model Context Protocol server that enables seamless integration with Freedcamp API for enterprise-level project management with advanced filtering, full CRUD operations, and extensive customization options.

SAP OData to MCP Server

Transforms SAP S/4HANA or ECC systems into conversational AI interfaces by exposing all OData services as dynamic MCP tools. Enables natural language interactions with ERP data for querying, creating, updating, and deleting business entities through SAP BTP integration.

MCP Servers for Teams

MCP 서버의 배포 예시

Bureau of Economic Analysis (BEA) MCP Server

Provides access to comprehensive U.S. economic data including GDP, personal income, and regional statistics via the Bureau of Economic Analysis API. It enables users to query datasets and retrieve specific economic indicators for states, counties, and industries through natural language.