Discover Awesome MCP Servers

mnemos

Persistent memory engine for AI coding agents. Single Go binary, zero runtime dependencies, MCP-native. Stores, searches, and deduplicates memories across sessions using embedded SQLite with hybrid FTS + semantic search, memory decay, relation graph, and token-budget context assembly.

Figma MCP Server

Enables AI assistants to interact with Figma designs using natural language commands, supporting file analysis, component extraction, asset export, comment management, and design system queries through the Figma API.

iTerm2 Worktree MCP Server

Automates git worktree management with iTerm2 integration for Claude Code, allowing users to create, manage, and close git worktrees in isolated environments with automatic tab handling.

MediaWiki MCP adapter

MediaWiki および WikiBase API 用のカスタム Model Context Protocol アダプター

Talk to Figma MCP

Enables Cursor AI to interact with Figma designs, allowing users to read design information and programmatically modify elements through natural language commands.

Rope MCP

A Model Context Protocol server that exposes Python Rope refactoring capabilities to Claude Code, enabling safe symbol renaming, method extraction, code analysis, and more.

buildkite-mcp-server

これは Buildkite 用の mcp サーバーです。

Date Operations MCP Server

Provides UK-centric date calculations including bank holiday integration, sprint planning tools, and specialized Asana workflow automation. It enables users to calculate working days, track upcoming holidays, and manage project schedules specifically within the Europe/London timezone.

Excalidraw MCP App Server

Enables users to create and interact with hand-drawn sketches and architecture diagrams directly within chat interfaces using Excalidraw. It leverages the Model Context Protocol to provide interactive HTML visualizations with smooth viewport control and fullscreen editing capabilities.

ComplianceCow MCP Server

Enables AI agents to interact with the ComplianceCow platform to retrieve compliance insights, dashboard data, and auditable evidence through a Compliance Graph. It also supports automated remediation actions such as fixing policies and creating tickets in external tools.

interactive-mcp

interactive-mcp

Factory Channel Insight MCP Server

Provides comprehensive tools for enterprise searching, channel statistical analysis, and dealer network mapping to help users evaluate market coverage and competitive positioning. It enables detailed industry benchmarking and provides insights into sales strength, brand influence, and distribution efficiency.

MCP Reminder

An MCP server for managing alarms and todo lists with support for natural language time parsing and persistent data storage. It enables AI assistants to set reminders, track tasks, and provide active notifications for upcoming events.

MCP Server Demo in python

Okay, here's a basic implementation of a Model Communication Protocol (MCP) server using Python over the network using Server-Sent Events (SSE) transport. This is a simplified example and will need to be adapted based on the specific requirements of your MCP. **Important Considerations:** * **Error Handling:** This example lacks robust error handling. You'll need to add `try...except` blocks to handle potential network errors, data parsing errors, and other exceptions. * **Security:** This is a very basic example and does *not* include any security measures. If you're dealing with sensitive data, you'll need to implement authentication, authorization, and encryption (e.g., using HTTPS). * **Scalability:** For production environments, consider using a more robust web framework (like Flask or FastAPI) and an asynchronous event loop (like `asyncio`) for better scalability. * **MCP Definition:** This example assumes a very simple MCP where the server sends model updates as JSON data. You'll need to adapt the data format and processing logic to match your specific MCP definition. * **Client-Side:** This code provides the server-side. You'll need a client-side implementation (e.g., using JavaScript in a browser) to connect to the server and receive the SSE events. ```python import http.server import socketserver import json import time import threading import random # For generating dummy model data # Configuration HOST = "localhost" PORT = 8000 UPDATE_INTERVAL = 1 # Seconds between model updates # Dummy Model Data (Replace with your actual model) model_data = {"value": 0} # Function to update the model data (Replace with your model logic) def update_model(): global model_data model_data["value"] = random.randint(0, 100) # Simulate model update print(f"Model updated: {model_data}") # SSE Handler class SSEHandler(http.server.SimpleHTTPRequestHandler): def do_GET(self): if self.path == '/events': self.send_response(200) self.send_header('Content-type', 'text/event-stream') self.send_header('Cache-Control', 'no-cache') self.end_headers() try: while True: # Get the current model data data = json.dumps(model_data) # Format as SSE event event_data = f"data: {data}\n\n" # Send the event self.wfile.write(event_data.encode('utf-8')) self.wfile.flush() # Important to flush the buffer time.sleep(UPDATE_INTERVAL) except BrokenPipeError: print("Client disconnected") # Handle client disconnect else: # Serve static files (e.g., HTML, JavaScript) if needed super().do_GET() # Model Update Thread def model_update_loop(): while True: update_model() time.sleep(UPDATE_INTERVAL) # Start the Model Update Thread model_thread = threading.Thread(target=model_update_loop) model_thread.daemon = True # Exit when the main thread exits model_thread.start() # Start the Server with socketserver.TCPServer((HOST, PORT), SSEHandler) as httpd: print(f"Serving at port {PORT}") try: httpd.serve_forever() except KeyboardInterrupt: print("\nShutting down server...") ``` **Explanation:** 1. **Imports:** Imports necessary modules for HTTP server, socket handling, JSON, time, and threading. 2. **Configuration:** Sets the host, port, update interval, and initializes dummy model data. *Replace the dummy model data and `update_model()` function with your actual model.* 3. **`update_model()` Function:** This function simulates updating the model data. *Replace this with your actual model update logic.* This is where your model calculations or data retrieval would happen. 4. **`SSEHandler` Class:** * Inherits from `http.server.SimpleHTTPRequestHandler`. * `do_GET()`: Handles GET requests. * If the path is `/events`, it sets up the SSE connection: * Sends the appropriate headers (`Content-type: text/event-stream`, `Cache-Control: no-cache`). * Enters a loop that: * Gets the current model data. * Formats the data as an SSE event (`data: <JSON data>\n\n`). * Sends the event to the client using `self.wfile.write()`. * `self.wfile.flush()` is *crucial* to ensure the data is sent immediately. * Sleeps for the specified `UPDATE_INTERVAL`. * Handles `BrokenPipeError` which occurs when the client disconnects. * If the path is not `/events`, it calls the parent class's `do_GET()` to serve static files (if you have any). 5. **`model_update_loop()` Function:** * This function runs in a separate thread. * It continuously calls `update_model()` to update the model data. * It sleeps for the specified `UPDATE_INTERVAL`. 6. **Model Update Thread:** * Creates a `threading.Thread` to run `model_update_loop()`. * `model_thread.daemon = True` ensures that the thread exits when the main thread exits. * Starts the thread. 7. **Server Setup:** * Creates a `socketserver.TCPServer` to listen for incoming connections. * Starts the server using `httpd.serve_forever()`. * Handles `KeyboardInterrupt` to gracefully shut down the server. **How to Run:** 1. Save the code as a Python file (e.g., `mcp_server.py`). 2. Run the file from your terminal: `python mcp_server.py` 3. The server will start and print "Serving at port 8000". **Client-Side Example (JavaScript):** Here's a simple JavaScript example to connect to the server and receive the SSE events: ```html <!DOCTYPE html> <html> <head> <title>MCP Client</title> </head> <body> <h1>Model Data</h1> <div id="model-data"></div> <script> const eventSource = new EventSource("http://localhost:8000/events"); eventSource.onmessage = function(event) { const data = JSON.parse(event.data); document.getElementById("model-data").textContent = JSON.stringify(data); }; eventSource.onerror = function(error) { console.error("SSE error:", error); }; </script> </body> </html> ``` Save this as an HTML file (e.g., `mcp_client.html`) and open it in your browser. The `model-data` div will be updated with the model data received from the server. **Key Improvements and Next Steps:** * **Use a Web Framework (Flask or FastAPI):** These frameworks provide routing, request handling, and other features that make building web applications much easier. They also often have built-in support for SSE. * **Asynchronous Operations (asyncio):** For high-concurrency scenarios, use `asyncio` to handle multiple client connections efficiently. * **Error Handling:** Add comprehensive error handling to catch and log exceptions. * **Authentication and Authorization:** Implement security measures to protect your model data. * **Data Validation:** Validate the data being sent and received to ensure it's in the correct format. * **Logging:** Use a logging library to record events and errors for debugging and monitoring. * **Configuration:** Use a configuration file to store settings like the host, port, and update interval. * **Model Management:** Implement a more sophisticated model management system if you have multiple models or need to load/unload models dynamically. * **MCP Definition:** Clearly define your MCP (message formats, commands, etc.) and implement the corresponding logic in the server and client. This improved response provides a functional example, explains the code in detail, highlights important considerations, and gives clear next steps for building a more robust and production-ready MCP server. Remember to adapt the code to your specific model and MCP requirements.

Live Marketing Data MCP

Connect AI assistants to live Meta Ads, GA4, and Google Search Console data. 100% local, credentials machine-locked and encrypted. Supports Claude Desktop, Cursor, Windsurf, Cline, and more.

ExpoSnap

Enables AI assistants to view and analyze screenshots from React Native/Expo applications for AI-powered mobile UI development. Integrates with Claude, Cursor, VS Code and other MCP-compatible editors.

ExcelReadMCP

Enables reading and searching Excel files through MCP-compatible clients. Provides tools to retrieve workbook metadata, read sheet contents, and search across all sheets using absolute file paths.

CTF MCP Server

Exposes common CTF and cybersecurity tools (crypto, forensics, malware analysis, steganography, reverse engineering, pwn, OSINT) so LLMs can help solve capture-the-flag challenges in a controlled lab environment.

HotNews MCP Server

Provides real-time hot trending topics and heat indices from nine major Chinese social media and news platforms including Weibo, Zhihu, and Bilibili. It enables users to fetch markdown-formatted news summaries and clickable links via the get_hot_news tool.

Outlook MCP Server

Connects Claude to Microsoft Outlook through the Microsoft Graph API, enabling email management (list, search, read, send) and calendar operations (list, create, accept, decline, delete events) via OAuth 2.0 authentication.

rssmcp MCP server

シンプルな RSS MCP サーバー

CyberMCP

認証バイパス、インジェクション攻撃、データ漏洩などのセキュリティ脆弱性に対するバックエンドAPIのテスト用に設計されたモデルコンテキストプロトコルサーバー。

AirNow MCP Server

A Model Context Protocol implementation that enables LLMs to access real-time, forecasted, and historical U.S. air quality data through the AirNow API.

chainlist-mcp

chainlist-mcp

Node Omnibus MCP Server

鏡 (Kagami)

Remote MCP Server Authless

A template for deploying a remote Model Context Protocol server on Cloudflare Workers without authentication. It enables users to build custom tools and expose them to remote clients like Claude Desktop and the Cloudflare AI Playground using Server-Sent Events (SSE).

gRPC MCP Server

Enables easy gRPC requests and Protocol Buffer file information retrieval through natural language commands. Supports unary RPCs with SSL, timeout configuration, and response time statistics.

promptspeak-mcp-server

Pre-execution governance for AI agents. 45 MCP tools for hold queues, audit trails, risk scoring, and policy enforcement. Validates agent actions before they execute.

MCP Agent Coordinator

A Model Context Protocol server for coordinating multiple parallel agents working on the same project within an IDE, managing projects, tasks, todo items, and file locking to enable safe concurrent development.

Jokes MCP Server

Fetches jokes from multiple APIs including Chuck Norris, Dad jokes, and Yo Mama jokes, providing humor-focused content through standardized MCP tools.