发现优秀的 MCP 服务器

MCP WeChat Official Accounts Spider

Enables AI agents to crawl, access, and analyze WeChat Official Account articles using Selenium and the Model Context Protocol. It provides specialized tools for dynamic content retrieval, image processing, and automated article analysis.

nodered-mcp

A Python MCP server that provides language models full read/write access to a Node-RED instance through its Admin HTTP API, enabling flow management with structured Pydantic responses and incremental patching.

contest-mcp-server

MCP server for searching and retrieving Korean contest information. Provides tools to search contests by keyword/category, get details, list categories, and find deadlines.

SAP Hybris C4C MCP Server by CData

This read-only MCP Server allows you to connect to SAP Hybris C4C data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp

attAck-mcp-server

这个项目是一个 MCP (模型上下文协议) 服务器，用于查询 ATT&CK (对抗性战术、技术和常识) 技术和战术。 它提供了一种访问和检索关于攻击者使用的各种攻击技术和战术信息的方法。

Revit MCP Server

Enables seamless communication between Claude AI and Autodesk Revit, allowing users to access and interact with Revit model information through natural language.

Readme Generator AI MCP

Readme Generator AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

mac-bridge-mcp

An MCP server that runs on a Mac and exposes a small, sharp set of tools (shell, file transfer, binary execution, screenshots) over a token-protected network port.

Giphy API MCP Server

An auto-generated Multi-Agent Conversation Protocol (MCP) Server that enables interaction with Giphy's API through natural language, allowing users to search, retrieve, and work with GIF content programmatically.

MCP Chat

Enables interactive chat with a local LLM using MCP architecture for document management, including tools to read, edit, and format documents.

Egnyte Large File Manager

Enables downloading real binary files from Egnyte and uploading large files with chunked support, complementing the official Egnyte MCP connector.

Simple_dart_mcp_server

以下是一个用 Dart 编写的非常简单的模型上下文协议服务器实现： ```dart import 'dart:io'; import 'dart:convert'; void main() async { final server = await ServerSocket.bind('localhost', 4040); print('服务器已启动，监听端口 ${server.port}'); server.listen((client) { handleClient(client); }); } void handleClient(Socket client) { print('客户端连接：${client.remoteAddress.address}:${client.remotePort}'); client.listen( (List<int> data) { final message = utf8.decode(data); print('收到消息：$message'); try { // 尝试解析 JSON final request = jsonDecode(message); // 模拟处理请求并生成响应 final response = processRequest(request); // 将响应编码为 JSON 并发送回客户端 final responseJson = jsonEncode(response); client.write(responseJson); print('发送响应：$responseJson'); } catch (e) { print('错误：无法解析 JSON 或处理请求：$e'); client.write('{"error": "Invalid request"}'); } }, onError: (error) { print('客户端错误：$error'); client.close(); }, onDone: () { print('客户端断开连接'); client.close(); }, ); } // 模拟处理请求的函数 Map<String, dynamic> processRequest(dynamic request) { // 在这里实现你的模型上下文逻辑 // 例如，根据请求中的参数执行某些操作并返回结果 // 示例：如果请求包含 "query" 字段，则返回一个包含 "response" 字段的响应 if (request is Map && request.containsKey('query')) { final query = request['query']; return {'response': '您查询的是：$query'}; } else { return {'error': '无效的请求格式'}; } } ``` **代码解释:** 1. **`import 'dart:io';` 和 `import 'dart:convert';`**: 导入必要的库，`dart:io` 用于网络操作，`dart:convert` 用于 JSON 编码和解码。 2. **`main()` 函数**: - 使用 `ServerSocket.bind()` 绑定服务器到 `localhost` 的 `4040` 端口。你可以根据需要更改端口。 - 使用 `server.listen()` 监听客户端连接。 - 对于每个连接的客户端，调用 `handleClient()` 函数来处理。 3. **`handleClient()` 函数**: - 打印客户端的连接信息。 - 使用 `client.listen()` 监听客户端发送的数据。 - **数据处理**: - 使用 `utf8.decode()` 将接收到的字节数据解码为字符串。 - 使用 `jsonDecode()` 尝试将字符串解析为 JSON 对象。 - 调用 `processRequest()` 函数来模拟处理请求并生成响应。 - 使用 `jsonEncode()` 将响应编码为 JSON 字符串。 - 使用 `client.write()` 将 JSON 字符串发送回客户端。 - **错误处理**: - 使用 `onError` 回调函数处理客户端错误。 - 使用 `onDone` 回调函数处理客户端断开连接。 4. **`processRequest()` 函数**: - 这是一个模拟函数，用于处理客户端的请求。 - 你需要根据你的模型上下文协议的实际需求来实现这个函数。 - 示例代码检查请求是否包含 "query" 字段，如果包含，则返回一个包含 "response" 字段的响应。 - 如果请求格式无效，则返回一个包含 "error" 字段的响应。 **如何运行:** 1. 将代码保存为 `server.dart` 文件。 2. 在终端中运行 `dart server.dart`。 **如何测试:** 你可以使用 `telnet` 或 `curl` 等工具来测试服务器。 **使用 `telnet`:** 1. 打开终端并运行 `telnet localhost 4040`。 2. 输入以下 JSON 字符串并按 Enter 键： ```json {"query": "你好"} ``` 3. 你应该会收到服务器的响应： ```json {"response": "您查询的是：你好"} ``` **使用 `curl`:** 1. 打开终端并运行以下命令： ```bash curl -X POST -H "Content-Type: application/json" -d '{"query": "你好"}' http://localhost:4040 ``` 2. 你应该会收到服务器的响应： ```json {"response": "您查询的是：你好"} ``` **重要说明:** * 这是一个非常简单的示例，仅用于演示模型上下文协议服务器的基本概念。 * 你需要根据你的实际需求来实现 `processRequest()` 函数，并添加必要的错误处理和安全性措施。 * 实际的模型上下文协议可能需要更复杂的协议和数据格式。 * 考虑使用更健壮的库，例如 `shelf` 或 `aqueduct`，来构建更复杂的服务器应用程序。 **中文总结:** 这段代码创建了一个简单的 Dart 服务器，监听 4040 端口。当客户端连接时，服务器接收客户端发送的 JSON 消息，然后调用 `processRequest()` 函数来处理请求并生成响应。最后，服务器将响应编码为 JSON 字符串并发送回客户端。 `processRequest()` 函数是一个占位符，你需要根据你的模型上下文协议的实际需求来实现它。 你可以使用 `telnet` 或 `curl` 等工具来测试服务器。 请记住，这只是一个简单的示例，你需要根据你的实际需求进行修改和扩展。

x-feed-mcp

A least-privilege, read-only MCP server that returns recent tweets from a set of tracked X (Twitter) accounts via a single tool.

runkeep-mcp

Enables management of long-running development processes (such as dev servers, compilers, and watchers) from MCP hosts. Provides tools to start, stop, restart, check status, view logs, and send input to managed processes.

Linux System MCP Server

Enables AI agents to interact with the Linux desktop through desktop notifications, interactive dialogs, shell command execution, and privileged command execution.

Xpenser

xpenser.cleverbrush.com is a ln open-source, self-hostable personal expense and income tracking app supporting different currencies, categories, vendors, automated invoice parsing, AI geberated reports and more.

Azure Database for PostgreSQL MCP Server (Preview)

Azure Database for PostgreSQL 托管控制平面服务器 (Azure Database for PostgreSQL Tuōguǎn Kòngzhì Píngmiàn Fúwùqì)

MCP Server Boilerplate

A starter template for building MCP (Model Context Protocol) servers that integrate with Claude, Cursor, or other MCP-compatible AI assistants. Provides a clean foundation with TypeScript support, example tool implementation, and installation scripts for quick customization.

Hello Service MCP Server

A unified HTTP/HTTPS service that exposes Model Context Protocol (MCP) functionality over HTTP endpoints, allowing clients to list available tools and call them through a standardized API.

mcp-movidesk

Enables natural language interaction with the Movidesk public API for managing tickets and persons/organizations, including CRUD operations and file attachments.

MCP Server for MySQL based on NodeJS

镜子 (jìng zi)

Cubism External Edit MCP

Wraps the Live2D Cubism Editor's external application integration API as MCP tools, enabling AI agents to control Cubism Editor for modeling operations via natural language.

ttrss-mcp

An MCP server that enables AI assistants to manage Tiny Tiny RSS feeds, including reading articles, updating statuses, and searching content. It also provides tools for feed management and generating automated daily reports.

protonmail-mcp-server

A read-only MCP server that connects to Proton Mail via Proton Bridge, enabling AI assistants to search, list, and read emails securely without leaving your machine.

mcp-sqlite

MCP server that provides SQLite database operations. Allows AI assistants to query, modify and manage SQLite databases through the Model Context Protocol.

MCP Podcast Scraper

An MCP server that scrapes and transcribes podcast episodes from YouTube or RSS feeds using Deepgram's Nova-2 model. It allows users to track podcasts for new episodes, manage transcripts, and generate personalized summaries through Claude.

🤖 Laravel Vibes

用于实现机器控制协议 (MCP) 服务器的 Laravel 扩展包

Infomate MCP

Fetches and provides curated tech news, trending topics, hot GitHub projects, and industry updates from infomate.club/vas3k. Enables users to stay updated with the latest developments in technology and programming through natural language queries.

spector-agent-mcp

AI-first WebGL 1/2 debugging MCP server that attaches to Chrome via CDP, enables frame capture and diagnostic analysis, and collaborates with Chrome DevTools MCP for agent-driven debugging workflows.

x-search-mcp

Enables real-time search of X (Twitter) posts, user timelines, and trends using either xAI's Responses API or the official X API v2.