发现优秀的 MCP 服务器

mcp-watermelon

MCP server for Watermelon.ai that exposes all 13 public API endpoints as tools, enabling AI assistants to manage contacts, conversations, messages, custom fields, and webhooks.

swiss-food-safety-mcp

MCP server connecting AI models to Swiss Federal Food Safety and Veterinary Office open data, enabling queries about food recalls, animal disease surveillance, food control results, and more.

MCP Web Chat

A server that enables WebChat functionality through MCP (Model-Control-Protocol), solving long-term connection issues while providing both common method calls and business API integration capabilities.

SAP Ariba Procurement MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for SAP Ariba Procurement (beta): https://www.cdata.com/download/download.aspx?sku=PAZK-V&type=beta

BlenderMCP

Connects Blender to Claude AI, enabling AI-assisted 3D modeling, scene creation, object manipulation, material control, and code execution directly in Blender through natural language prompts.

Directmedia MCP

Provides programmatic access to the Directmedia Publishing 'Digitale Bibliothek' collection, a 1990s German electronic book library containing 101 volumes of classic literature and philosophy with text extraction, search, and navigation capabilities.

天气 MCP 服务器

这是一个基于 FastMCP 构建的天气查询 MCP 服务器。 (This translates to: "This is a weather query MCP server built on FastMCP.")

OpenFeature MCP Server

Provides OpenFeature SDK installation guidance for various programming languages and enables feature flag evaluation through the OpenFeature Remote Evaluation Protocol (OFREP). Supports multiple AI clients and can connect to any OFREP-compatible feature flag service.

mcp-stackexchange

Wraps the StackExchange API v2.3 to enable reading StackExchange data (questions, answers, etc.) without authentication. Allows AI agents to query StackExchange content through natural language or direct tool calls.

aris-md/mcp

A minimal, well-structured MCP server implementation for learning and experimentation that exposes three tools: web search, API search, and client ID processing. It demonstrates clean separation between tool, transport, and LLM layers while supporting multiple AI clients through the Model Context Protocol standard.

LeetCode MCP (Model Context Protocol)

Okay, I understand. You want to use an MCP (presumably referring to a "Minecraft Protocol" server, though the connection to LeetCode is unclear) to generate LeetCode notes. This is a bit of an unusual request, and I need to make some assumptions to provide a helpful translation. Here's the breakdown and possible interpretations, along with translations: **Understanding the Request (and Assumptions):** * **"MCP Server":** I'm assuming you're *not* actually talking about a Minecraft server. It's more likely you're using "MCP" as shorthand for some kind of **"Machine Comprehension Program"** or a similar AI-powered system. This makes more sense in the context of generating notes. If you *are* talking about a Minecraft server, please clarify how you intend to use it for LeetCode notes! * **"Generate Leetcode Notes":** You want to automatically create notes, summaries, or explanations for LeetCode problems. This could involve: * Summarizing problem statements. * Generating code solutions (in various languages). * Explaining the logic behind solutions. * Creating test cases. * Providing time and space complexity analysis. **Possible Scenarios and Translations:** Based on the assumption that "MCP Server" refers to an AI-powered system, here are a few ways to phrase your request in Chinese, depending on the specific nuance you want to convey: **Scenario 1: General Request (Using an AI system to create LeetCode notes):** * **Chinese:** 使用机器学习系统生成 LeetCode 笔记 (Shǐyòng jīqì xuéxí xìtǒng shēngchéng LeetCode bǐjì) * **Literal Translation:** Use a machine learning system to generate LeetCode notes. * **Explanation:** This is a broad and general translation. It assumes the "MCP Server" is a machine learning system. **Scenario 2: More Specific (Using a server-based AI to generate LeetCode notes):** * **Chinese:** 使用服务器端的 AI 系统生成 LeetCode 笔记 (Shǐyòng fúwùqì duān de AI xìtǒng shēngchéng LeetCode bǐjì) * **Literal Translation:** Use a server-side AI system to generate LeetCode notes. * **Explanation:** This emphasizes that the AI is running on a server. **Scenario 3: Focusing on Automation (Automated generation of LeetCode notes):** * **Chinese:** 自动化生成 LeetCode 笔记 (Zìdòng huà shēngchéng LeetCode bǐjì) * **Literal Translation:** Automatically generate LeetCode notes. * **Explanation:** This focuses on the automated aspect, without explicitly mentioning the AI system. It implies that some system is doing the generation. **Scenario 4: If you *really* meant Minecraft (highly unlikely, but just in case):** * **Chinese:** 使用 Minecraft 服务器生成 LeetCode 笔记 (Shǐyòng Minecraft fúwùqì shēngchéng LeetCode bǐjì) * **Literal Translation:** Use a Minecraft server to generate LeetCode notes. * **Explanation:** This is the literal translation if you meant a Minecraft server. It's highly improbable that this is what you meant, as the connection is unclear. You would need to explain *how* you intend to use a Minecraft server for this. Perhaps you're thinking of using command blocks or a mod to create a visual representation of algorithms? **Key Vocabulary:** * **LeetCode:** LeetCode (No translation needed, it's a proper noun) * **笔记 (bǐjì):** Notes * **生成 (shēngchéng):** To generate, to produce * **机器学习 (jīqì xuéxí):** Machine learning * **人工智能 (réngōng zhìnéng) / AI:** Artificial intelligence / AI * **服务器 (fúwùqì):** Server * **自动化 (zìdòng huà):** Automation, automated **To get a more accurate translation, please provide more context:** * **What is the "MCP Server" you are referring to?** Is it a specific software, a type of AI, or something else? * **What kind of notes do you want to generate?** Summaries, code solutions, explanations, test cases, etc.? * **What is the purpose of generating these notes?** Studying, sharing, etc.? The more information you give me, the better I can tailor the translation to your specific needs.

MemoraМCP

An MCP-powered storage system for AI agents that provides IPFS-secured, verifiable, and sovereign data storage capabilities.

Todo MCP Server

A TypeScript-based server that enables AI agents to create, prioritize, and manage ordered task lists for complex projects. It provides tools for task tracking, status filtering, and progress statistics with persistent storage.

insights-mcp-server

红帽 Insights MCP 服务器 POC (Hóngmào Insights MCP fúwùqì POC) This translates to: * **红帽 (Hóngmào):** Red Hat * **Insights:** Insights (The English word is often used directly in Chinese in technical contexts) * **MCP:** MCP (The English abbreviation is often used directly in Chinese in technical contexts) * **服务器 (fúwùqì):** Server * **POC:** POC (Proof of Concept - The English abbreviation is often used directly in Chinese in technical contexts) Therefore, a more natural translation, especially in a technical setting, might be: **红帽 Insights MCP 服务器概念验证 (Hóngmào Insights MCP fúwùqì gàiniàn yànzhèng)** Where: * **概念验证 (gàiniàn yànzhèng):** Concept Validation (This is a more formal translation of "Proof of Concept") While the first translation is perfectly understandable, the second one is more precise and commonly used in formal documentation. Choose the one that best suits your audience and the context.

arxiv-mcp

A streamlined MCP server that connects AI assistants to arXiv's vast collection of academic papers, enabling search, retrieval, and analysis of research papers.

Sample Model Context Protocol Demos

好的，这是关于如何将模型上下文协议与 AWS 结合使用的一些示例： **总览** 模型上下文协议 (Model Context Protocol, MCP) 是一种标准化方法，用于将上下文信息传递给机器学习模型。这使得模型能够根据手头的任务更好地理解和响应。在 AWS 环境中，MCP 可以与各种服务集成，以增强模型的性能和可解释性。 **使用场景和示例** 以下是一些使用 MCP 与 AWS 结合的常见场景和示例： * **个性化推荐:** * **场景:** 构建一个推荐系统，根据用户的历史行为、人口统计信息和当前上下文（例如，一天中的时间、位置）来推荐产品或内容。 * **如何使用 MCP:** * 将用户历史行为、人口统计信息和上下文信息编码为 MCP 格式。 * 将 MCP 数据传递给您的推荐模型（例如，在 Amazon SageMaker 上部署的模型）。 * 模型使用 MCP 数据来生成个性化推荐。 * **AWS 服务:** Amazon Personalize, Amazon SageMaker, Amazon DynamoDB (存储用户数据), Amazon Location Service (获取位置信息) * **示例代码 (伪代码):** ```python # 假设我们已经从 DynamoDB 获取了用户数据，并从 Location Service 获取了位置信息 user_id = "user123" user_data = get_user_data_from_dynamodb(user_id) location_data = get_location_data_from_location_service(user_id) # 构建 MCP 数据 mcp_data = { "user_id": user_id, "user_history": user_data["purchase_history"], "user_age": user_data["age"], "location": location_data["city"], "time_of_day": "evening" } # 将 MCP 数据传递给 SageMaker 模型 response = sagemaker_endpoint.invoke(mcp_data) # 从响应中获取推荐结果 recommendations = response["recommendations"] ``` * **欺诈检测:** * **场景:** 检测金融交易中的欺诈行为，考虑交易金额、交易地点、用户行为模式等上下文信息。 * **如何使用 MCP:** * 将交易金额、交易地点、用户行为模式等信息编码为 MCP 格式。 * 将 MCP 数据传递给您的欺诈检测模型。 * 模型使用 MCP 数据来评估交易的欺诈风险。 * **AWS 服务:** Amazon Fraud Detector, Amazon SageMaker, Amazon Kinesis (实时数据流), Amazon DynamoDB (存储用户行为数据) * **示例代码 (伪代码):** ```python # 假设我们已经从 Kinesis 获取了实时交易数据 transaction_data = get_transaction_data_from_kinesis() # 构建 MCP 数据 mcp_data = { "transaction_amount": transaction_data["amount"], "transaction_location": transaction_data["location"], "user_behavior": get_user_behavior_from_dynamodb(transaction_data["user_id"]) } # 将 MCP 数据传递给 Fraud Detector 或 SageMaker 模型 fraud_score = fraud_detector.detect_fraud(mcp_data) # 或 sagemaker_endpoint.invoke(mcp_data) # 根据欺诈评分采取行动 if fraud_score > threshold: flag_transaction_as_fraudulent() ``` * **自然语言处理 (NLP):** * **场景:** 提高文本分类、情感分析或机器翻译等 NLP 任务的准确性，通过提供文档的上下文信息（例如，作者、来源、主题）。 * **如何使用 MCP:** * 将文档内容、作者、来源、主题等信息编码为 MCP 格式。 * 将 MCP 数据传递给您的 NLP 模型。 * 模型使用 MCP 数据来更好地理解文本并提高性能。 * **AWS 服务:** Amazon Comprehend, Amazon SageMaker, Amazon S3 (存储文档), Amazon Kendra (企业搜索) * **示例代码 (伪代码):** ```python # 假设我们已经从 S3 获取了文档 document = get_document_from_s3("s3://my-bucket/my-document.txt") # 构建 MCP 数据 mcp_data = { "document_content": document, "document_author": "John Doe", "document_source": "News Article", "document_topic": "Politics" } # 将 MCP 数据传递给 Comprehend 或 SageMaker 模型 sentiment = comprehend.detect_sentiment(mcp_data) # 或 sagemaker_endpoint.invoke(mcp_data) # 分析情感 print(f"Sentiment: {sentiment}") ``` * **图像识别:** * **场景:** 提高图像识别的准确性，通过提供图像的上下文信息（例如，拍摄地点、时间、天气）。 * **如何使用 MCP:** * 将图像数据、拍摄地点、时间、天气等信息编码为 MCP 格式。 * 将 MCP 数据传递给您的图像识别模型。 * 模型使用 MCP 数据来更好地识别图像中的对象。 * **AWS 服务:** Amazon Rekognition, Amazon SageMaker, Amazon S3 (存储图像), Amazon Location Service (获取位置信息) * **示例代码 (伪代码):** ```python # 假设我们已经从 S3 获取了图像 image = get_image_from_s3("s3://my-bucket/my-image.jpg") # 获取图像的元数据 (例如，通过 EXIF 数据) image_metadata = get_image_metadata(image) # 构建 MCP 数据 mcp_data = { "image_data": image, "location": image_metadata["location"], "time": image_metadata["time"], "weather": get_weather_data_from_location_service(image_metadata["location"]) } # 将 MCP 数据传递给 Rekognition 或 SageMaker 模型 objects = rekognition.detect_objects(mcp_data) # 或 sagemaker_endpoint.invoke(mcp_data) # 识别图像中的对象 print(f"Objects detected: {objects}") ``` **关键考虑因素:** * **数据格式:** 定义清晰的 MCP 数据格式，以便模型能够正确解析和使用上下文信息。 可以使用 JSON 或其他结构化数据格式。 * **数据量:** 考虑 MCP 数据的大小和复杂性，以及它对模型性能的影响。 优化数据传输和处理流程。 * **安全性:** 确保 MCP 数据的安全性，特别是当包含敏感信息时。 使用 AWS Identity and Access Management (IAM) 控制访问权限。 * **模型训练:** 在训练模型时，使用包含上下文信息的 MCP 数据，以便模型能够学习如何利用这些信息。 * **模型部署:** 确保模型部署环境能够接收和处理 MCP 数据。 可以使用 Amazon SageMaker Endpoints 或其他部署选项。 * **监控:** 监控模型的性能，并根据需要调整 MCP 数据或模型参数。 使用 Amazon CloudWatch 监控指标。 **总结:** 模型上下文协议 (MCP) 是一种强大的工具，可以提高机器学习模型的性能和可解释性。 通过将 MCP 与 AWS 服务集成，您可以构建更智能、更个性化的应用程序。 以上示例展示了 MCP 在不同场景下的应用，并提供了使用 AWS 服务的指导。 请根据您的具体需求进行调整和扩展。 希望这些示例对您有所帮助！ 如果您有任何其他问题，请随时提出。

caniuse-mcp

An MCP server that provides browser compatibility data and web API support information using caniuse.com, MDN BCD, and Web Features, enabling developers to check feature support across browsers and against browserslist configurations.

WordPress MCP Server

Enables comprehensive management of WordPress sites including posts, users, media, categories, tags, and site settings via the WordPress REST API.

mcp-edge-search

一个模型上下文协议（Model Context Protocol，MCP）服务器，为像 Claude Desktop 这样的 MCP 客户端提供网络搜索功能。

Toy MCP Server

A simple reference implementation demonstrating MCP server basics with two toy tools: generating random animals and simulating 20-sided die rolls.

Jira Extended MCP Server

Enables AI agents to manage Jira Cloud projects with full CRUD operations, bulk actions, sprint and release management, and issue linking using natural language.

diff-explainer

AI-powered git diff analysis with human-readable explanations, risk flags, and review checklists. Enables to explain any diff text or currently staged git changes through an MCP server.

fallcorp-mcp

Exposes foldkit's 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client, enabling state folding, band classification, and crease pattern checks.

mcp-database

Read-only MySQL/MariaDB MCP server for running SELECT queries safely, with automatic read-only enforcement and query limits.

Yandex Webmaster MCP Server

MCP server that provides 46 tools for managing Yandex Webmaster API v4, enabling site management, sitemaps, indexing, search analytics, and more through natural language.

Interactive Feedback MCP

MCP server that enables human-in-the-loop workflow in AI-assisted development tools by allowing users to provide direct feedback to AI agents without consuming additional premium requests.

ltspice-mcp

An MCP server that enables LLMs to read and modify LTspice schematics, run simulations, parse results, and generate plots, all through natural language.

🤖 MCP Server — Agent X (Powered by Gemini Flash + Twitter API)

使用 MCP 服务器构建的 AI 代理

LumenX-MCP Legal Spend Intelligence Server

MCP server that enables intelligent analysis of legal spend data across multiple sources (LegalTracker, databases, CSV/Excel files), providing features like spend summaries, vendor performance analysis, and budget comparisons.

willow-mcp

An agent-neutral MCP server providing SQLite key/value storage, Postgres knowledge base, and Kart task queue functionality. Features SAP/1.0 authorization on every tool call for secure multi-application access.