发现优秀的 MCP 服务器
通过 MCP 服务器扩展您的代理能力,拥有 86,267 个能力。
WhatsApp Web MCP
一个桥梁,使用模型上下文协议将 WhatsApp 网页版连接到 AI 模型,从而使 Claude 和其他 AI 系统能够通过标准化的界面与 WhatsApp 进行交互。
translator-ai
Enables translation of JSON i18n files to multiple languages using various AI providers (Google Gemini, OpenAI, Ollama/DeepSeek) with intelligent caching and deduplication.
Google Search MCP Server
An MCP server that provides Google Search functionality with automatic API key rotation and intelligent quota management, enabling natural language search queries with advanced filtering options.
@aryaminus/socials-mcp
Enables social media creators to pull TikTok, Instagram, Facebook, and YouTube analytics into a persistent vault, receive weekly digests, review scripts, build media kits, and draft brand outreach using official APIs only.
Harvey Intel
Solana token safety analysis, CORTEX trading signals, and Synthia social intelligence. Pay-per-query via x402 USDC micropayments.
rednote-mind-mcp
Enables AI assistants to search Xiaohongshu notes, analyze favorites, and extract text from images for social media research.
ChillMCP
Enables AI agents to take breaks and manage stress levels through 8 different break activities like watching Netflix, coffee breaks, and bathroom breaks. Features automatic stress accumulation, boss alert systems, and natural language commands for work-life balance simulation.
Remote MCP Server
A Cloudflare Workers-based server that implements the Model Context Protocol (MCP), allowing AI assistants like Claude to access custom tools without authentication.
mysqlDbMcp
Production-grade MySQL MCP server with multi-source YAML config, read-only default, supporting metadata inspection, querying, and optional modules via stdio or HTTP.
telegram-mcp-kit
Exposes the Telegram Bot API as tools for Claude Code or any MCP client, enabling message sending, chat management, file handling, and bot information retrieval.
china-phone-mcp
Enables AI agents to look up Chinese phone number carrier and location information using MIIT official data.
Bot12 MCP Server
Converts your bot12 trading bot into tools for Claude and other AI assistants, providing pre-built trading operations, account management, and reporting features.
mcp-sqlserver
Enables AI assistants to connect to Microsoft SQL Server for schema discovery, querying, stored procedures, DDL, performance diagnostics, and developer utilities with configurable security modes.
hardened-terminal-mcp
Security-hardened MCP server that runs only allowlisted commands with no shell, jailed to a single directory, and bounded execution.
taw-computer
An MCP server that provides AI agents with a full Ubuntu desktop environment inside Docker, enabling them to perform complex computer tasks like browsing, coding, testing, and GUI automation.
Algorand MCP Server
Enables interaction with the Algorand blockchain network including account management, payments, asset creation and transfers, along with general utility tools. Provides secure mnemonic encryption and supports both testnet and mainnet environments.
spekoai-mcp
A Model Context Protocol server that provides voice-AI session management and usage tracking tools for SpekoAI. It enables creating, retrieving, and ending voice sessions while monitoring usage through MCP clients like Claude Desktop.
Cityflo OTP MCP
Provides on-time performance analysis for Mumbai North bus routes via tools for route summaries, late trip drill-down, and data quality reports. It quarantines invalid data and surfaces policy questions instead of hidden normalizations.
OpenEHR MCP Server
Enables LLMs to interact with OpenEHR electronic health record systems by retrieving clinical archetypes, generating AQL queries from natural language, and executing queries against on-premise EHR databases. Supports OpenEHR Clinical Knowledge Manager integration and custom IIS-hosted EHR APIs for comprehensive medical data access.
Vocab Voyage
Vocabulary tools for SAT, ISEE, SSAT, GRE, GMAT, LSAT, PSAT prep — Word of the Day, definitions, multiple-choice quizzes, course word lists, and 7-day study plan previews. 13 test-prep courses. Hosted MCP server with MCP Apps UI widgets. No install required. Optional scoped personal tokens.
addgene-mcp
MCP server for Addgene plasmid repository, enabling AI assistants to search, filter, and retrieve plasmid data including sequences and metadata.
mcp-ytTranscript
好的,以下是一个简单的 MCP(最小可行产品)服务器,它使用 URL 和所需语言返回 YouTube 视频的转录: ```python from flask import Flask, request, jsonify from youtube_transcript_api import YouTubeTranscriptApi app = Flask(__name__) @app.route('/transcribe', methods=['GET']) def transcribe_youtube_video(): """ 从 YouTube 视频获取转录。 请求参数: url (str): YouTube 视频的 URL。 language (str, optional): 所需的转录语言代码(例如,'en' 代表英语,'zh-CN' 代表简体中文)。默认为 'en'。 返回: JSON: 包含转录文本的 JSON 对象。如果出现错误,则返回错误消息。 """ try: url = request.args.get('url') language = request.args.get('language', 'en') # 默认为英语 if not url: return jsonify({'error': '必须提供 YouTube 视频 URL。'}), 400 # 从 URL 中提取视频 ID video_id = url.split("watch?v=")[1] if "&" in video_id: video_id = video_id.split("&")[0] # 获取转录 transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=[language]) # 将转录转换为文本 text = '\n'.join([entry['text'] for entry in transcript]) return jsonify({'transcript': text}) except Exception as e: return jsonify({'error': str(e)}), 500 if __name__ == '__main__': app.run(debug=True) ``` **代码解释:** 1. **导入必要的库:** * `flask`: 用于创建 Web 服务器。 * `youtube_transcript_api`: 用于从 YouTube 获取转录。 2. **创建 Flask 应用:** * `app = Flask(__name__)` 创建一个 Flask 应用实例。 3. **定义路由 `/transcribe`:** * `@app.route('/transcribe', methods=['GET'])` 定义一个 GET 请求的路由,当用户访问 `/transcribe` 时,会执行 `transcribe_youtube_video` 函数。 4. **`transcribe_youtube_video` 函数:** * **获取请求参数:** * `url = request.args.get('url')` 从请求参数中获取 YouTube 视频的 URL。 * `language = request.args.get('language', 'en')` 从请求参数中获取所需的语言代码,如果没有提供,则默认为英语 ('en')。 * **验证 URL:** * `if not url:` 检查是否提供了 URL,如果没有,则返回一个错误消息。 * **提取视频 ID:** * 从 URL 中提取 YouTube 视频的 ID。 这段代码假设 URL 格式为 `https://www.youtube.com/watch?v=VIDEO_ID`。 * **获取转录:** * `transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=[language])` 使用 `youtube_transcript_api` 获取指定语言的转录。 * **将转录转换为文本:** * `text = '\n'.join([entry['text'] for entry in transcript])` 将转录条目连接成一个字符串,每个条目之间用换行符分隔。 * **返回 JSON 响应:** * `return jsonify({'transcript': text})` 将转录文本作为 JSON 对象返回。 * **错误处理:** * `try...except` 块用于捕获可能发生的异常,例如无法找到转录或网络错误。如果发生错误,则返回一个包含错误消息的 JSON 对象。 5. **运行应用:** * `if __name__ == '__main__':` 确保只有在直接运行脚本时才执行以下代码。 * `app.run(debug=True)` 启动 Flask 开发服务器,`debug=True` 启用调试模式,方便开发。 **如何使用:** 1. **安装依赖:** ```bash pip install flask youtube-transcript-api ``` 2. **运行脚本:** ```bash python your_script_name.py ``` 3. **发送请求:** 使用浏览器或 `curl` 等工具发送 GET 请求到 `/transcribe` 路由,并提供 `url` 和 `language` 参数。 例如: ```bash curl "http://127.0.0.1:5000/transcribe?url=https://www.youtube.com/watch?v=dQw4w9WgXcQ&language=zh-CN" ``` 将 `https://www.youtube.com/watch?v=dQw4w9WgXcQ` 替换为实际的 YouTube 视频 URL,并将 `zh-CN` 替换为所需的语言代码。 **重要注意事项:** * **错误处理:** 这个 MCP 包含基本的错误处理,但你应该根据你的需求添加更详细的错误处理。 * **API 限制:** YouTube Transcript API 可能有速率限制。 如果你的应用需要处理大量的请求,你可能需要考虑使用 API 密钥或实现缓存机制。 * **转录可用性:** 并非所有 YouTube 视频都有自动生成的转录,并且并非所有转录都提供所有语言版本。 你的代码应该能够处理这些情况。 * **安全性:** 在生产环境中,你应该使用更安全的 Web 服务器,例如 Gunicorn 或 uWSGI,并配置 HTTPS。 * **URL 解析:** URL 解析代码比较简单,可能无法处理所有可能的 YouTube URL 格式。 你可以使用更健壮的 URL 解析库,例如 `urllib.parse`。 **中文翻译:** 好的,这是一个简单的最小可行产品 (MVP) 服务器,它使用 URL 和所需的语言返回 YouTube 视频的字幕: ```python from flask import Flask, request, jsonify from youtube_transcript_api import YouTubeTranscriptApi app = Flask(__name__) @app.route('/transcribe', methods=['GET']) def transcribe_youtube_video(): """ 从 YouTube 视频获取字幕。 请求参数: url (str): YouTube 视频的 URL。 language (str, optional): 所需的字幕语言代码(例如,'en' 代表英语,'zh-CN' 代表简体中文)。默认为 'en'。 返回: JSON: 包含字幕文本的 JSON 对象。如果出现错误,则返回错误消息。 """ try: url = request.args.get('url') language = request.args.get('language', 'en') # 默认为英语 if not url: return jsonify({'error': '必须提供 YouTube 视频 URL。'}), 400 # 从 URL 中提取视频 ID video_id = url.split("watch?v=")[1] if "&" in video_id: video_id = video_id.split("&")[0] # 获取字幕 transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=[language]) # 将字幕转换为文本 text = '\n'.join([entry['text'] for entry in transcript]) return jsonify({'transcript': text}) except Exception as e: return jsonify({'error': str(e)}), 500 if __name__ == '__main__': app.run(debug=True) ``` **代码解释:** 1. **导入必要的库:** * `flask`: 用于创建 Web 服务器。 * `youtube_transcript_api`: 用于从 YouTube 获取字幕。 2. **创建 Flask 应用:** * `app = Flask(__name__)` 创建一个 Flask 应用实例。 3. **定义路由 `/transcribe`:** * `@app.route('/transcribe', methods=['GET'])` 定义一个 GET 请求的路由,当用户访问 `/transcribe` 时,会执行 `transcribe_youtube_video` 函数。 4. **`transcribe_youtube_video` 函数:** * **获取请求参数:** * `url = request.args.get('url')` 从请求参数中获取 YouTube 视频的 URL。 * `language = request.args.get('language', 'en')` 从请求参数中获取所需的语言代码,如果没有提供,则默认为英语 ('en')。 * **验证 URL:** * `if not url:` 检查是否提供了 URL,如果没有,则返回一个错误消息。 * **提取视频 ID:** * 从 URL 中提取 YouTube 视频的 ID。 这段代码假设 URL 格式为 `https://www.youtube.com/watch?v=VIDEO_ID`。 * **获取字幕:** * `transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=[language])` 使用 `youtube_transcript_api` 获取指定语言的字幕。 * **将字幕转换为文本:** * `text = '\n'.join([entry['text'] for entry in transcript])` 将字幕条目连接成一个字符串,每个条目之间用换行符分隔。 * **返回 JSON 响应:** * `return jsonify({'transcript': text})` 将字幕文本作为 JSON 对象返回。 * **错误处理:** * `try...except` 块用于捕获可能发生的异常,例如无法找到字幕或网络错误。如果发生错误,则返回一个包含错误消息的 JSON 对象。 5. **运行应用:** * `if __name__ == '__main__':` 确保只有在直接运行脚本时才执行以下代码。 * `app.run(debug=True)` 启动 Flask 开发服务器,`debug=True` 启用调试模式,方便开发。 **如何使用:** 1. **安装依赖:** ```bash pip install flask youtube-transcript-api ``` 2. **运行脚本:** ```bash python your_script_name.py ``` 3. **发送请求:** 使用浏览器或 `curl` 等工具发送 GET 请求到 `/transcribe` 路由,并提供 `url` 和 `language` 参数。 例如: ```bash curl "http://127.0.0.1:5000/transcribe?url=https://www.youtube.com/watch?v=dQw4w9WgXcQ&language=zh-CN" ``` 将 `https://www.youtube.com/watch?v=dQw4w9WgXcQ` 替换为实际的 YouTube 视频 URL,并将 `zh-CN` 替换为所需的语言代码。 **重要注意事项:** * **错误处理:** 这个 MVP 包含基本的错误处理,但你应该根据你的需求添加更详细的错误处理。 * **API 限制:** YouTube Transcript API 可能有速率限制。 如果你的应用需要处理大量的请求,你可能需要考虑使用 API 密钥或实现缓存机制。 * **字幕可用性:** 并非所有 YouTube 视频都有自动生成的字幕,并且并非所有字幕都提供所有语言版本。 你的代码应该能够处理这些情况。 * **安全性:** 在生产环境中,你应该使用更安全的 Web 服务器,例如 Gunicorn 或 uWSGI,并配置 HTTPS。 * **URL 解析:** URL 解析代码比较简单,可能无法处理所有可能的 YouTube URL 格式。 你可以使用更健壮的 URL 解析库,例如 `urllib.parse`。 This code provides a basic, functional server. Remember to handle potential errors and limitations as mentioned above for a more robust application. Good luck!
Bastion
A local-first control plane for AI agent tools, providing policy enforcement, spend caps, rate limiting, and audit trails for MCP servers.
BabyBuddy MCP Server
Integrates with self-hosted BabyBuddy to log and retrieve baby care data such as feedings, sleep, diaper changes, and measurements via natural language.
oscine
An MCP server that exposes a synthesizer composer's command catalog as tools, enabling Claude to compose, sound-design, and mix in a live browser session.
ds-pilot
MCP server that exposes your design system components and tokens to AI agents, preventing duplicate component creation and hardcoded token values.
chrome-mcp
Enables controlling a real Chrome browser from MCP hosts like Claude, with extension-based or CDP fallback, supporting tabs, navigation, interaction, and page reading tools.
AgentVault
MCP server for AI-native credential management, enabling agents to securely store, retrieve, and manage API keys with encryption, spending budgets, and audit logging.
Image Generation Worker Template
Okay, here's a translation of "Template to easily make an MCP server on Cloudflare" into Chinese, along with a few options depending on the nuance you want to convey: **Option 1 (Most Literal & General):** * **模板,用于在 Cloudflare 上轻松创建 MCP 服务器** * (Mó bǎn, yòng yú zài Cloudflare shàng qīngsōng chuàngjiàn MCP fúwùqì) * This is a direct translation. "模板" (mó bǎn) means "template," "用于" (yòng yú) means "used for," "在 Cloudflare 上" (zài Cloudflare shàng) means "on Cloudflare," "轻松创建" (qīngsōng chuàngjiàn) means "easily create," and "MCP 服务器" (MCP fúwùqì) means "MCP server." **Option 2 (Slightly More Natural & Emphasizing Ease):** * **在 Cloudflare 上快速搭建 MCP 服务器的模板** * (Zài Cloudflare shàng kuàisù dājiàn MCP fúwùqì de mó bǎn) * This version uses "快速搭建" (kuàisù dājiàn), which means "quickly set up" or "quickly build," which might sound more appealing than just "easily create." The "的" (de) connects the phrase to the template. **Option 3 (Focusing on Simplified Setup):** * **简化在 Cloudflare 上设置 MCP 服务器的模板** * (Jiǎnhuà zài Cloudflare shàng shèzhì MCP fúwùqì de mó bǎn) * This option uses "简化设置" (jiǎnhuà shèzhì), meaning "simplified setup." It emphasizes that the template makes the setup process easier. **Which option is best depends on the specific context:** * If you want a very straightforward and literal translation, use **Option 1**. * If you want to emphasize the speed and ease of setup, use **Option 2**. * If you want to highlight the simplified nature of the setup process, use **Option 3**. **Important Considerations:** * **"MCP"**: It's assumed that "MCP" is an acronym that doesn't need translation. If "MCP" has a standard Chinese translation in the context you're using it, you should use that instead of just writing "MCP." For example, if it stands for "Minecraft Protocol," you might translate it as "我的世界协议" (Wǒ de shìjiè xiéyì). *However, without knowing what MCP stands for, I've left it as "MCP" in the translations.* * **Target Audience:** Consider your target audience. If they are very technical, a more literal translation might be fine. If they are less technical, a more descriptive and user-friendly translation might be better. Choose the option that best fits your needs!
Xcode Diagnostics MCP Plugin
连接到 Xcode 的构建系统,以提取、解析和显示 Swift 项目中的错误和警告,帮助 AI 助手快速识别代码问题,而无需手动搜索构建日志。