发现优秀的 MCP 服务器

s-GitHubTestRepo-HJA3

从 MCP 服务器演示创建。

BRAINS OS - version MCP

一个使用 SST、React 和 AWS 构建的 Serverless MCP 实现。

Weather Java SSE Transport MCP Service

使用 Jetty 实现的 Java 模型上下文协议 SSE HTTP 服务器

Memory Cache Server

镜子 (jìng zi)

Speikzeug

用于自动化数据处理和系统匿名化的，集成了 MCP 服务器的现代化工具集。

MCP Server - Oracle DB Context

为处理大型 Oracle 数据库的 MCP 服务器

Cloudera Iceberg MCP Server (via Impala)

通过 Impala 使用 Cloudera Iceberg MCP 服务器

Anyquery

使用单个二进制文件连接到 40 多个应用程序

TimezoneToolkit MCP Server

提供全面时间和时区工具的高级 MCP 服务器。

MCP Iceberg Catalog

用于与 Apache Iceberg 目录交互的 MCP 服务器，允许通过 LLM 提示进行数据湖发现和元数据搜索。

Knesset MCP Server

用于访问以色列议会信息的 Model Context Protocol (MCP) 服务器

Knowledge Graph Memory Server

镜子 (jìng zi)

mcp-servers

MCP 服务器赋予 LLM 超能力

MCP (Model Context Protocol) 介紹

MCP 天气服务器的演示项目。

OpenRouter Search MCP Server

为 OpenRouter 搜索功能提供的 MCP 服务器

mcp-cbs-cijfers-open-data

用于处理 CBS 统计开放数据的 MCP 服务器

📚 PDF Reader MCP

一个使用 Node.js/TypeScript 构建的 MCP 服务器，允许 AI 代理安全地读取 PDF 文件（本地或 URL），并提取文本、元数据或页数。使用 pdf-parse 库。

Task Researcher

好的，这是对您描述的翻译： **中文翻译：** 人工智能编码研究员，负责分析任务复杂度，并运行深度研究（STORM），将复杂任务分解为子任务，作为 MCP 服务器或命令行界面 (CLI)。 **一些补充说明，以确保翻译的准确性：** * **人工智能编码研究员 (Rén gōng zhì néng biān mǎ yán jiū yuán):** This is a direct translation of "AI Coding Researcher." * **分析任务复杂度 (Fēn xī rèn wù fù zá dù):** This translates to "analyzes task complexity." * **运行深度研究 (Yùn xíng shēn dù yán jiū):** This translates to "runs deep research." * **STORM:** Since "STORM" is an acronym, you might consider keeping it in English, or providing a Chinese translation of what it stands for if it's relevant to your audience. For example, if STORM stands for "Systematic Task Organization and Refinement Method," you could add "(系统化任务组织与精炼方法)" after it. However, if it's just a project name, keeping it as "STORM" is fine. * **将复杂任务分解为子任务 (Jiāng fù zá rèn wù fēn jiě wéi zǐ rèn wù):** This translates to "decompose complex tasks into subtasks." * **MCP 服务器 (MCP fú wù qì):** This translates to "MCP Server." * **命令行界面 (Mìng lìng háng jiè miàn):** This translates to "Command Line Interface (CLI)." You can also use the abbreviation "CLI" directly in Chinese, as it's becoming increasingly common in technical contexts. Therefore, a slightly more nuanced translation could be: **人工智能编码研究员，负责分析任务复杂度，并运行深度研究 (STORM)，将复杂任务分解为子任务，并将其实现为 MCP 服务器或命令行界面 (CLI)。** This adds the phrase "并将其实现为" (bìng jiāng qí shí xiàn wéi), which means "and implement it as," making the sentence flow a bit better.

MCP Server (Mortgage Comparison Platform)

用于将贷款估算 (LE) 和结算单 (CD) PDF 解析为符合 MISMO 标准的 JSON 格式，并使用 LLM 增强上下文信息的规范 MCP 服务器。专为 AI 驱动的抵押贷款自动化、合规性和决策而构建。

Server

Okay, here's a basic outline and code snippets for a simple "Weather MCP" (presumably meaning "Minecraft Protocol") server in Python. I'll break it down into sections and explain the key concepts. Keep in mind that this is a *very* simplified example and doesn't implement the full Minecraft protocol. It's designed to illustrate the core idea of a server that responds to Minecraft client requests with weather data. **Important Considerations:** * **Minecraft Protocol Complexity:** The actual Minecraft protocol is complex and constantly evolving. This example *does not* implement it fully. It's a simplified demonstration. For real Minecraft server development, you'd need a robust library like `mcstatus` or a more complete server implementation. * **MCP (Minecraft Coder Pack):** MCP is primarily for *modding* the Minecraft client and server, not for creating entirely new servers. I'm assuming you're using "MCP" loosely to mean "something that interacts with Minecraft." * **Weather Data Source:** This example uses a placeholder for weather data. You'll need to integrate a real weather API (e.g., OpenWeatherMap, AccuWeather) to get actual weather information. * **Security:** This is a basic example and doesn't include any security measures. Real Minecraft servers need proper security to prevent exploits. **Conceptual Outline:** 1. **Socket Setup:** Create a TCP socket to listen for incoming connections from Minecraft clients (or a proxy/mod that simulates a client). 2. **Client Connection Handling:** When a client connects, accept the connection and create a new thread or process to handle it. 3. **Simplified Protocol:** Define a very simple protocol for the client to request weather data. For example, the client might send a specific string like "WEATHER_REQUEST". 4. **Weather Data Retrieval:** When a request is received, fetch weather data from your chosen source (API or placeholder). 5. **Response Formatting:** Format the weather data into a string or a simple data structure that the client can understand. 6. **Sending the Response:** Send the formatted weather data back to the client through the socket. 7. **Closing the Connection:** Close the connection with the client. **Python Code (Illustrative Example):** ```python import socket import threading import time # For simulating weather updates import random # For simulating weather updates # Configuration HOST = '127.0.0.1' # Listen on localhost PORT = 25566 # Choose a port (not the default Minecraft port) WEATHER_REQUEST_COMMAND = "WEATHER_REQUEST" SIMULATE_WEATHER = True # Set to False if using a real API # Placeholder for weather data (replace with API integration) weather_data = { "temperature": 25, "condition": "Clear", "humidity": 60 } def update_weather(): """Simulates weather updates (replace with API calls).""" global weather_data while SIMULATE_WEATHER: weather_data["temperature"] = random.randint(15, 35) conditions = ["Clear", "Rain", "Cloudy", "Thunderstorm"] weather_data["condition"] = random.choice(conditions) weather_data["humidity"] = random.randint(40, 80) print(f"Weather updated: {weather_data}") time.sleep(60) # Update every 60 seconds def handle_client(conn, addr): """Handles a single client connection.""" print(f"Connected by {addr}") try: while True: data = conn.recv(1024) # Receive up to 1024 bytes if not data: break # Client disconnected message = data.decode('utf-8').strip() print(f"Received: {message}") if message == WEATHER_REQUEST_COMMAND: # Format the weather data into a string weather_string = f"Temperature: {weather_data['temperature']}°C, Condition: {weather_data['condition']}, Humidity: {weather_data['humidity']}%" conn.sendall(weather_string.encode('utf-8')) else: conn.sendall("Unknown command".encode('utf-8')) except Exception as e: print(f"Error handling client: {e}") finally: conn.close() print(f"Connection closed with {addr}") def start_server(): """Starts the weather server.""" server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM) server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1) # Avoid address already in use error try: server_socket.bind((HOST, PORT)) server_socket.listen() print(f"Weather server listening on {HOST}:{PORT}") # Start the weather update thread if SIMULATE_WEATHER: weather_thread = threading.Thread(target=update_weather) weather_thread.daemon = True # Exit when the main thread exits weather_thread.start() while True: conn, addr = server_socket.accept() client_thread = threading.Thread(target=handle_client, args=(conn, addr)) client_thread.start() except Exception as e: print(f"Server error: {e}") finally: server_socket.close() if __name__ == "__main__": start_server() ``` **Explanation:** 1. **Imports:** Imports necessary modules: `socket` for network communication, `threading` for handling multiple clients concurrently, `time` for simulating weather updates, and `random` for generating random weather data. 2. **Configuration:** * `HOST`: The IP address to listen on (localhost in this case). * `PORT`: The port number to listen on. Choose a port that's not already in use. *Do not use the default Minecraft port (25565) unless you know what you're doing.* * `WEATHER_REQUEST_COMMAND`: The string that the client sends to request weather data. * `SIMULATE_WEATHER`: A flag to control whether to simulate weather updates or use a real API. 3. **`weather_data`:** A dictionary to store the current weather information. This is a placeholder; you'll replace this with data from a real weather API. 4. **`update_weather()`:** This function simulates weather updates. It randomly changes the temperature, condition, and humidity every 60 seconds. *Replace this with code that calls a weather API.* The `time.sleep(60)` call pauses the thread for 60 seconds. The `weather_thread.daemon = True` line ensures that the thread exits when the main program exits. 5. **`handle_client(conn, addr)`:** This function handles the communication with a single client. * It receives data from the client using `conn.recv(1024)`. * It decodes the data from bytes to a string using `data.decode('utf-8')`. * It checks if the received message is the `WEATHER_REQUEST_COMMAND`. * If it is, it formats the weather data into a string and sends it back to the client using `conn.sendall(weather_string.encode('utf-8'))`. The `encode('utf-8')` converts the string to bytes before sending. * If the message is not recognized, it sends an "Unknown command" message. * It closes the connection using `conn.close()`. 6. **`start_server()`:** This function sets up the server socket and listens for incoming connections. * It creates a TCP socket using `socket.socket(socket.AF_INET, socket.SOCK_STREAM)`. * It binds the socket to the specified host and port using `server_socket.bind((HOST, PORT))`. * It starts listening for connections using `server_socket.listen()`. * It enters a loop that accepts incoming connections using `server_socket.accept()`. * For each connection, it creates a new thread to handle the client using `threading.Thread(target=handle_client, args=(conn, addr))`. * It starts the thread using `client_thread.start()`. * The `server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)` line is important. It allows you to quickly restart the server after it crashes or is stopped without getting an "Address already in use" error. 7. **`if __name__ == "__main__":`:** This ensures that the `start_server()` function is only called when the script is run directly (not when it's imported as a module). **How to Run:** 1. Save the code as a Python file (e.g., `weather_server.py`). 2. Run the script from your terminal: `python weather_server.py` **Client-Side (Simplified Example - Requires Modification for Minecraft):** This is a *very* basic Python client to test the server. **This will NOT work directly with Minecraft.** You'll need to adapt it to send the request from within a Minecraft mod or through a proxy. ```python import socket HOST = '127.0.0.1' PORT = 25566 WEATHER_REQUEST_COMMAND = "WEATHER_REQUEST" with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) s.sendall(WEATHER_REQUEST_COMMAND.encode('utf-8')) data = s.recv(1024) print('Received:', repr(data.decode('utf-8'))) ``` **Important Notes and Next Steps:** * **Minecraft Integration:** The biggest challenge is integrating this with Minecraft. You'll need to: * **Create a Minecraft Mod:** This is the most common approach. Your mod would need to: * Establish a connection to your Python server. * Send the `WEATHER_REQUEST_COMMAND`. * Receive the weather data. * Display the weather data in the game (e.g., in the chat, on a custom GUI). * **Use a Proxy:** You could create a proxy server that sits between the Minecraft client and the real Minecraft server. The proxy would intercept weather-related packets and replace them with data from your Python server. This is more complex. * **Weather API Integration:** Replace the placeholder weather data with calls to a real weather API. You'll need to: * Sign up for an API key from a weather service (e.g., OpenWeatherMap). * Install the `requests` library: `pip install requests` * Modify the `update_weather()` function to make API calls. * **Error Handling:** Add more robust error handling to the server and client code. * **Data Formatting:** Consider using a more structured data format like JSON for sending weather data between the server and client. This will make it easier to parse the data on the client side. * **Security:** Implement security measures to protect your server from unauthorized access. **Example of Weather API Integration (OpenWeatherMap):** ```python import requests # Replace with your OpenWeatherMap API key API_KEY = "YOUR_OPENWEATHERMAP_API_KEY" CITY = "London" # Or any city you want def get_weather_from_api(): """Gets weather data from OpenWeatherMap.""" url = f"http://api.openweathermap.org/data/2.5/weather?q={CITY}&appid={API_KEY}&units=metric" try: response = requests.get(url) response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx) data = response.json() weather_data = { "temperature": data["main"]["temp"], "condition": data["weather"][0]["description"], "humidity": data["main"]["humidity"] } return weather_data except requests.exceptions.RequestException as e: print(f"Error fetching weather data: {e}") return None # In your update_weather() function: def update_weather(): global weather_data while SIMULATE_WEATHER: new_weather = get_weather_from_api() if new_weather: weather_data = new_weather print(f"Weather updated from API: {weather_data}") else: print("Failed to update weather from API.") time.sleep(60) ``` Remember to replace `"YOUR_OPENWEATHERMAP_API_KEY"` with your actual API key. You'll also need to adjust the `CITY` variable to the city you want weather data for. This comprehensive explanation and code should give you a solid starting point for building your weather MCP server in Python. Good luck!

awsome-kali-MCPServers

awsome kali MCPServers 是一套专为 Kali Linux 定制的 MCP 服务器，旨在增强 AI 代理在逆向工程和安全测试方面的能力。它提供灵活的网络分析、目标嗅探、流量分析、二进制理解和自动化功能，从而提升 AI 驱动的工作流程。

MedixHub Model Context Protocol (MCP) Server

MedixHub - 具有一系列医疗和健康护理 API 和工具的模型上下文协议 (MCP) 服务器。

testmcpgithubdemo1

从 MCP 服务器演示创建。