发现优秀的 MCP 服务器

jira-mcp

A token-lean MCP server for Jira Cloud that enables natural language interaction with issues, comments, transitions, and more through a set of seven normalized tools, reducing token usage via field allowlists and ADF-to-Markdown conversion.

Gmail MCP Server

Integrates with Gmail APIs to manage emails and labels, including sending, deleting, summarizing, and semantic search via RAG.

codegraph

Indexes a codebase into a live symbol graph and serves it via MCP to AI coding tools for context-aware code queries.

LinkedIn Automated Post Creator

Automates the creation and scheduling of LinkedIn posts using MCP server integration, allowing users to manage content and automatically publish to their LinkedIn accounts.

Hacker News MCP Server

A read-only MCP server that enables browsing stories, reading comments, searching posts, and viewing user profiles on Hacker News.

Portfolio MCP

Enables AI assistants to query a person's CV and portfolio content via MCP tools and resources, returning grounded answers from local markdown data instead of relying on resume parsing.

lexos-compliance-mcp

A compliance tracking and document drafting MCP server for the LexOS platform, providing tools for client management, deadline tracking, Google Calendar sync, client-facing status and chase policies, and AI-powered document drafting.

MCP Server Starter

一个生产就绪的模板，用于在 TypeScript 中构建模型上下文协议服务器，使用 Bun 提供快速开发，Biome 进行代码检查，并实现自动化版本管理。

mcp-practice

MCP server for Cursor that automates HR tasks such as employee onboarding, intranet guidance, time-off and leave requests, and meeting room booking.

slack-mcp

Enables comprehensive interaction with Slack workspaces, allowing users to manage channels, send messages, and search history. It supports managing reminders, pins, reactions, and user information through the Model Context Protocol.

DER BA: Nada Consta

MCP server for querying DER BA's official 'Nada Consta' records, read-only and pay-per-use, compatible with any MCP client.

Universal Clipboard MCP

Enables seamless content conversion between multiple formats including Markdown, HTML, and DOCX directly within development environments.

Gmail MCP Connector

A Gmail MCP server running on Cloudflare Workers that enables reading, searching, labeling, drafting, sending, and managing Gmail messages, including fetching raw attachment bytes, with per-user OAuth authorization.

mcp-server-truster

Enables querying domain trust scores, ratings, and reviews, searching domains, and posting reviews via natural language through the truster.info service.

metabase-mcp-server

Enables AI agents to read-onlyly access Metabase instances, query databases using MBQL or SQL, explore schemas, run saved questions, and export data.

layercake

A local MCP server that connects AI agents to Adobe After Effects, enabling reliable project inspection, reasoning, and controlled mutations through structured tools and typed patches.

git-commit-aider MCP Server

Makes git commits on behalf of AI by appending "(aider)" to the committer's name, allowing tracking of AI contributions in your codebase.

sfinance-mcp-server

Provides access to Indian stock market data via screener.in, enabling stock analysis, document access, screening, and more through MCP.

Microsoft SQL Server MCP Server

Enables AI assistants to connect and query Microsoft SQL Server databases using natural language, executing read-only SQL queries for safe data inspection and analysis.

mcp-vision-server

Enables image analysis, OCR, and text-to-image generation through OpenAI-compatible APIs. Supports local paths, URLs, or base64 images with configurable models and backup endpoints.

mcp-tools

Collection of MCP servers for Forgejo, NetBox, Authentik, and CouchDB, enabling issue tracking, device management, authentication, and database operations via MCP and CLI.

mcp-google-sheets

A Python-based MCP server that acts as a bridge between MCP-compatible clients and the Google Sheets API, enabling AI-driven automation and data manipulation workflows.

pathmark

Local-first memory for MCP clients. It provides shared durable memory without requiring hosted accounts, vector databases, or API keys, and works with Codex, Claude Code, Cursor, and other MCP clients.

Feishu MCP Server

一个基于 MCP 的服务，使 AI 模型能够无缝地与飞书平台交互，支持文档阅读和聊天机器人消息功能。

MCP Multi-Tool Server

Provides calculator tools for mathematical operations, access to TypeScript SDK documentation, and meeting summary prompt templates through both stdio and SSE transports.

gpt-game-arena

This MCP server enables playing chess, Quick Go (9x9), Go (13x13), and Real Go (19x19) against GPT, with a React widget UI, deterministic difficulty-aware move selection, and authoritative rules/session handling for both ChatGPT plugin and standalone preview modes.

ParamPilot MCP

Enables interaction with ParamPilot's campaign optimization platform via Model Context Protocol, providing tools for campaign management, experiments, and model jobs with configurable safety profiles.

OpenClaw MCP Server

MCP server that exposes OpenClaw Gateway tools to Claude Code and other MCP clients, enabling messaging, session management, scheduling, node control, web search, memory search, and TTS.

Birding Buddy MCP

An AI-powered birding companion that connects Claude to eBird and Xeno-canto APIs, enabling personalized birding with life list tracking, route-based hotspot discovery, and recording enrichment.

Tamagotchi MCP Server

好的，以下是一個簡化的 Tamagotchi MCP (Minecraft Protocol) 伺服器實現，模擬電子雞遊戲。 這個範例會使用 Python 和 `mcstatus` 庫來處理 Minecraft 協議。 **重要說明:** * **簡化:** 這是一個非常簡化的版本，僅用於演示概念。 它不會實現完整的 Minecraft 伺服器功能。 * **mcstatus:** 這個範例依賴於 `mcstatus` 庫。 你需要先安裝它： `pip install mcstatus` * **安全性:** 這個範例沒有考慮任何安全性問題。 不要在生產環境中使用。 * **MCP 限制:** 真正的 Minecraft 協議非常複雜。 這個範例只處理最基本的部分，例如伺服器列表查詢。 * **沒有遊戲邏輯:** 這個範例只模擬伺服器存在，沒有實際的電子雞遊戲邏輯。 你需要自己添加遊戲邏輯。 **程式碼 (Python):** ```python import socket import json import time from mcstatus import MinecraftServer # 電子雞狀態 (你可以擴展這個) tamagotchi_name = "小雞" tamagotchi_health = 100 tamagotchi_hunger = 50 tamagotchi_happiness = 75 # 伺服器設定 server_ip = "127.0.0.1" # 本機 IP server_port = 25565 # Minecraft 預設端口 def create_status_response(): """建立 Minecraft 伺服器狀態回應 (JSON 格式).""" status = { "version": { "name": "Tamagotchi Server 1.0", "protocol": 757 # Minecraft 1.16.5 協議版本 (範例) }, "players": { "max": 1, # 最大玩家數 "online": 0, # 線上玩家數 "sample": [] # 玩家列表 (空) }, "description": { "text": f"歡迎來到 {tamagotchi_name} 的世界！\n健康: {tamagotchi_health}, 飢餓: {tamagotchi_hunger}, 快樂: {tamagotchi_happiness}" }, "favicon": "data:image/png;base64,<你的favicon base64 編碼>" # 可選: 伺服器圖示 } return json.dumps(status) def handle_connection(client_socket): """處理客戶端連線.""" try: # 接收客戶端傳送的資料 data = client_socket.recv(1024) if not data: return # 處理握手封包 (0x00) if data[0] == 0x00: # 讀取協議版本、伺服器位址和端口 protocol_version = data[1] server_address_length = data[2] server_address = data[3:3 + server_address_length].decode('utf-8') server_port = int.from_bytes(data[3 + server_address_length:5 + server_address_length], 'big') next_state = data[5 + server_address_length] # 回應握手封包 (空封包) client_socket.send(bytes([0x00])) # 處理狀態請求 (0x00) data = client_socket.recv(1024) if data[0] == 0x00: # 建立狀態回應 status_response = create_status_response() # 建立狀態回應封包 response_bytes = bytes([0x00]) + len(status_response.encode('utf-8')).to_bytes(1, 'big') + status_response.encode('utf-8') # 發送狀態回應 client_socket.send(response_bytes) # 處理 Ping 請求 (0x01) data = client_socket.recv(1024) if data[0] == 0x01: # 回應 Ping 請求 client_socket.send(data) except Exception as e: print(f"處理連線時發生錯誤: {e}") finally: client_socket.close() def main(): """主程式.""" server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM) server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1) # 允許重複使用位址 server_socket.bind((server_ip, server_port)) server_socket.listen(5) # 最多允許 5 個連線 print(f"Tamagotchi 伺服器正在運行於 {server_ip}:{server_port}...") try: while True: client_socket, client_address = server_socket.accept() print(f"接受來自 {client_address} 的連線") handle_connection(client_socket) # 模擬電子雞狀態變化 (你可以根據實際遊戲邏輯修改) global tamagotchi_health, tamagotchi_hunger, tamagotchi_happiness tamagotchi_health -= 1 tamagotchi_hunger += 2 tamagotchi_happiness -= 0.5 # 限制數值範圍 tamagotchi_health = max(0, min(100, tamagotchi_health)) tamagotchi_hunger = max(0, min(100, tamagotchi_hunger)) tamagotchi_happiness = max(0, min(100, tamagotchi_happiness)) time.sleep(5) # 每 5 秒更新一次狀態 except KeyboardInterrupt: print("伺服器關閉") finally: server_socket.close() if __name__ == "__main__": main() ``` **使用方法:** 1. **安裝 `mcstatus`:** `pip install mcstatus` 2. **儲存程式碼:** 將程式碼儲存為 `tamagotchi_server.py` (或其他你喜歡的名稱)。 3. **執行程式:** `python tamagotchi_server.py` 4. **在 Minecraft 中新增伺服器:** 在 Minecraft 啟動器中，新增一個伺服器，位址設定為 `127.0.0.1:25565`。 5. **查看伺服器列表:** 在 Minecraft 中，進入多人遊戲，你會看到你的 Tamagotchi 伺服器。 伺服器描述會顯示電子雞的狀態。 **程式碼說明:** * **`create_status_response()`:** 建立一個 JSON 字串，包含 Minecraft 伺服器狀態資訊。 這個資訊會顯示在 Minecraft 伺服器列表中。 你可以修改這個函數來顯示更多關於電子雞的資訊。 * **`handle_connection()`:** 處理客戶端連線。 這個函數接收客戶端傳送的資料，並根據 Minecraft 協議回應。 這個範例只處理握手和狀態請求。 * **`main()`:** 主程式。 這個函數建立一個 socket 伺服器，監聽連線，並處理每個連線。 它還模擬電子雞的狀態變化。 * **電子雞狀態:** `tamagotchi_name`, `tamagotchi_health`, `tamagotchi_hunger`, `tamagotchi_happiness` 這些變數儲存電子雞的狀態。 你可以擴展這些變數來儲存更多資訊，例如電子雞的年齡、心情等等。 * **狀態變化:** 在 `main()` 函數的 `while` 迴圈中，電子雞的狀態會定期更新。 你可以根據實際的遊戲邏輯修改這些更新。 * **錯誤處理:** 程式碼包含基本的錯誤處理，但你可以根據需要添加更多錯誤處理。 **如何擴展這個範例:** * **添加遊戲邏輯:** 這是最重要的部分。 你需要添加程式碼來處理玩家的輸入，並根據這些輸入來更新電子雞的狀態。 例如，你可以添加指令來餵食電子雞、和電子雞玩耍等等。 * **使用資料庫:** 如果你想儲存電子雞的狀態，你可以使用資料庫。 * **使用 GUI:** 你可以使用 GUI 庫 (例如 Tkinter 或 PyQt) 來建立一個圖形介面，讓玩家可以更方便地與電子雞互動。 * **實現完整的 Minecraft 協議:** 如果你想讓你的伺服器更像一個真正的 Minecraft 伺服器，你需要實現更多的 Minecraft 協議。 這是一個非常複雜的任務。 **重要提示:** * 這個範例是一個非常簡化的版本，僅用於演示概念。 * 真正的 Minecraft 協議非常複雜。 * 這個範例沒有考慮任何安全性問題。 * 你需要自己添加遊戲邏輯。 希望這個範例能幫助你開始建立你的 Tamagotchi MCP 伺服器！