Discover Awesome MCP Servers

DataForSEO MCP Server

DataForSEO API と Model Context Protocol を介してやり取りを可能にする stdio ベースのサーバーです。これを使用すると、検索結果、キーワードデータ、被リンク、オンページ分析など、さまざまな SEO データを取得できます。

Metaso MCP Server

Provides AI-powered web search, full-page content extraction, and search-enhanced Q\&A capabilities via the Metaso AI search engine. It enables large language models to access diverse information across web, academic, and multimedia sources with structured Markdown or JSON output.

Gallica/BnF MCP Server

Enables access to the Gallica digital library of the Bibliothèque nationale de France (BnF) with search capabilities across titles, authors, subjects, and dates, plus retrieval of document metadata, IIIF images, and OCR text content.

Horse Racing News

Retrieves and displays the latest horse racing news stories from Thoroughbred Daily News RSS feed, including titles, content, and links.

GitLab MCP Server

Connects AI assistants to GitLab, enabling natural language queries to view merge requests, review discussions, test reports, pipeline status, and respond to comments directly from chat.

Mood Playlist MCP Server

Generates personalized music playlists based on mood analysis using AI sentiment detection and emoji understanding. Integrates with Last.fm API to create playlists with multi-language support and provides streaming links for Spotify, Apple Music, and YouTube.

Remote MCP Server with WorkOS AuthKit

An example MCP server that allows remote clients to connect and authenticate using WorkOS AuthKit, providing organization-centric authentication with permission-based access control for tools.

Nara Market FastMCP Server

Provides access to South Korean government procurement (G2B) and Nara Market shopping mall data, enabling users to search bid announcements, procurement statistics, product catalogs, and contract information through 15 specialized tools.

Zephyr MCP Server

A lightweight server that simplifies building and flashing Zephyr RTOS projects through a REST API, allowing remote control of the microcontroller programming workflow.

MCP client-server

Okay, I understand you want me to create a basic client-server program using the Minecraft Communications Protocol (MCP). However, there are a few important points to consider: * **MCP is not a standard, well-defined protocol.** It's more of a general term for communication between Minecraft clients and servers, and it's constantly evolving with each Minecraft version. There's no single, official MCP specification. * **Reverse Engineering:** Implementing MCP requires reverse engineering the Minecraft client and server, which can be complex and potentially violate the Minecraft EULA (End User License Agreement). * **Complexity:** A full MCP implementation is a significant undertaking. It involves handling packet structures, compression, encryption, authentication, and game logic. * **Alternatives:** If you want to interact with a Minecraft server, consider using existing libraries like: * **Minecraft Protocol Library (MCProtocolLib):** A Java library for interacting with Minecraft servers. * **Python Minecraft Protocol (pyminecraft):** A Python library for interacting with Minecraft servers. * **Other libraries:** Search for libraries in your preferred language. **Given these limitations, I will provide a simplified example that demonstrates the basic concept of sending and receiving data using sockets, which is the foundation of MCP communication. This example will NOT be a fully functional MCP client/server, but it will illustrate the core principles.** **Important Disclaimer:** This code is for educational purposes only and is not a complete MCP implementation. It will not connect to a real Minecraft server. Using this code to interact with a real Minecraft server may violate the Minecraft EULA. **Example (Python):** ```python import socket # Server-side def server(): host = '127.0.0.1' # Localhost port = 25565 # Example port (not the real Minecraft port) server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM) server_socket.bind((host, port)) server_socket.listen(1) # Listen for one connection print(f"Server listening on {host}:{port}") conn, addr = server_socket.accept() print(f"Connection from {addr}") while True: data = conn.recv(1024) # Receive up to 1024 bytes if not data: break # Connection closed message = data.decode('utf-8') print(f"Received: {message}") response = f"Server received: {message}".encode('utf-8') conn.sendall(response) conn.close() server_socket.close() print("Server closed") # Client-side def client(): host = '127.0.0.1' port = 25565 client_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM) try: client_socket.connect((host, port)) print(f"Connected to {host}:{port}") message = "Hello from the client!" client_socket.sendall(message.encode('utf-8')) data = client_socket.recv(1024) response = data.decode('utf-8') print(f"Received: {response}") except socket.error as e: print(f"Socket error: {e}") finally: client_socket.close() print("Client closed") if __name__ == "__main__": import threading server_thread = threading.Thread(target=server) server_thread.start() # Give the server a moment to start import time time.sleep(0.1) client() server_thread.join() # Wait for the server thread to finish ``` **Explanation:** 1. **`server()` function:** * Creates a socket, binds it to a host and port, and listens for incoming connections. * Accepts a connection from a client. * Enters a loop to receive data from the client, decode it, print it, and send a response back. * Closes the connection and the socket. 2. **`client()` function:** * Creates a socket and connects to the server. * Sends a message to the server. * Receives a response from the server, decodes it, and prints it. * Closes the socket. 3. **`if __name__ == "__main__":` block:** * Starts the server in a separate thread so that the client can connect to it. * Calls the `client()` function to run the client. * Waits for the server thread to finish. **How to Run:** 1. Save the code as a Python file (e.g., `mcp_example.py`). 2. Run the file from your terminal: `python mcp_example.py` **Important Considerations:** * **Error Handling:** The code includes basic error handling, but you should add more robust error handling for production use. * **Data Serialization:** In a real MCP implementation, you would need to serialize and deserialize data into specific packet formats. This example uses simple strings. * **Threading:** The server uses threading to handle multiple clients concurrently. * **Port:** The example uses port 25565. This is *not* the actual Minecraft server port (which is 25565 by default, but can be changed). This example uses a different port to avoid conflicts and because it's not a real Minecraft server. * **Security:** This example does not include any security measures (encryption, authentication). A real MCP implementation would require these. **Next Steps (If you want to explore further):** 1. **Research Minecraft Protocol:** Search for documentation or reverse-engineered specifications of the Minecraft protocol for the specific version you are interested in. Be aware that this information may be incomplete or inaccurate. 2. **Use a Library:** Consider using an existing library (MCProtocolLib, pyminecraft, etc.) to handle the low-level details of the protocol. 3. **Start Small:** Begin by implementing a simple feature, such as sending a chat message or retrieving server status. 4. **Be Aware of the EULA:** Make sure your project complies with the Minecraft EULA. This example provides a starting point for understanding the basic concepts of client-server communication. Building a full MCP client/server is a complex task that requires significant effort and knowledge. Remember to use existing libraries whenever possible and to be mindful of the Minecraft EULA.

Spider MCP Server

Enables crawling and extracting clean content from documentation websites with optional LLM-powered analysis for intelligent summaries, code example extraction, and content classification.

MCP-Server-and-client-Implementation-on-Linux

Linux 上での MCP (Minecraft Protocol) サーバーおよびクライアントの実装 (Claude Desktop を使用するのではなく)

service-economics

Free service management tools — playbooks, benchmarks, and instant service health analysis. DigitalCore MCP gives you free access to service management expertise directly in your AI assistant. Run a Service Reality Check to score your service health in 60 seconds. Access strategy playbooks for ser

MCP Slack Python

An MCP server that enables interaction with Slack workspaces through tools for managing channels, sending messages, and retrieving user profiles. It leverages the Slack API and FastMCP to provide functionalities like message history lookup and reaction management.

Sugar CRM MCP Server by CData

This read-only MCP Server allows you to connect to Sugar CRM data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp

MCP Dungeon Game

An idle dungeon crawler game playable through conversation, featuring equipment collection, time-based dungeon exploration, auto-battles, random events, and encrypted local save data.

SimpleWeatherForecastServer

SimpleWeatherForecastServer

MCP Server (Mortgage Comparison Platform)

ローン見積書（LE）およびクロージング・ディスクロージャー（CD）のPDFを、MISMO準拠のJSONに解析し、LLM（大規模言語モデル）で強化されたコンテキストを付与する、正規のMCPサーバー。AI駆動型の住宅ローン自動化、コンプライアンス、および意思決定のために構築されています。

FeedbackBasket MCP Server

Model Context Protocol server that enables AI assistants to query and analyze project feedback and bug reports from FeedbackBasket projects, with filtering by category, status, sentiment, and search capabilities.

funding-rates-mcp

funding-rates-mcp

MCP Software Engineer

Enables Claude to function as a full-stack software engineer with comprehensive development capabilities including project creation, database management, frontend/backend development, testing, deployment, and DevOps operations across multiple frameworks and technologies.

mcp-servers

MCPサーバーでLLMにスーパーパワーを付与する

Figma MCP Server

A Python implementation of the Model Context Protocol server that enables AI assistants to interact with Figma through WebSocket connections, allowing them to read, analyze, and export design data.

Ambiance MCP Server

Provides intelligent code context and analysis through semantic compression, AST parsing, and multi-language support. Offers 60-80% token reduction while enabling AI assistants to understand codebases through local analysis, OpenAI-enhanced insights, and GitHub repository integration.

awsome-kali-MCPServers

awsome kali MCPServers は、Kali Linux 向けに調整された MCP サーバーのセットで、リバースエンジニアリングやセキュリティテストにおける AI エージェントの能力を強化するように設計されています。柔軟なネットワーク分析、ターゲットスニッフィング、トラフィック分析、バイナリ理解、自動化を提供し、AI 主導のワークフローを向上させます。

Japanese Vocab Anki MCP Server

A Model Context Protocol server that enables language models to interact with Anki flashcard decks programmatically, with specialized features for Japanese language learning including vocabulary import, sample sentence generation, and spaced repetition review.

FinRAG-MCP

Enables secure role-based querying of company documents across different departments (Engineering, Finance, HR, Marketing) with access control that restricts data visibility based on user roles. Provides retrieval-augmented generation with source citations and metadata for trusted corporate knowledge access.

MCP Document Processor

An intelligent document processing system that automatically classifies, extracts information from, and routes business documents using the Model Context Protocol (MCP).

Portfolio Tracker MCP Server

Enables AI clients to track investment portfolios by retrieving positions, calculating profit and loss, and refreshing price data via Yahoo Finance. It allows users to monitor overall performance and query specific ticker details through natural language interactions.

Model Context Protocol Server

A stateful gateway server for AI applications that solves the memory limitations of Large Language Models by maintaining separate conversation contexts for each user.