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 26,408 个能力。

全部26,408
AiDex

AiDex

MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.

Postgres MCP Pro

Postgres MCP Pro

Enables comprehensive PostgreSQL database management including index tuning, query plan analysis, health monitoring, schema-aware SQL generation, and safe SQL execution with configurable access control for both development and production environments.

TheGraph MCP Server

TheGraph MCP Server

一个 MCP 服务器,它使用来自 The Graph 的索引区块链数据来驱动 AI 代理。

Korean Law MCP Server

Korean Law MCP Server

Enables real-time search and analysis of Korean laws, legal precedents, and administrative rules through the National Law Information Center Open API, allowing AI agents to access official legal information for contract review, compliance, and legal research.

mcp-hfspace MCP Server

mcp-hfspace MCP Server

将 Claude Desktop 连接到 Hugging Face Spaces,只需最少的设置,即可实现图像生成、视觉任务、文本转语音以及与 AI 模型聊天等功能。

K8s Doctor MCP

K8s Doctor MCP

AI-powered Kubernetes diagnostics that analyzes pod crashes, logs, and cluster health to provide root cause analysis and actionable solutions for common issues like CrashLoopBackOff, OOM kills, and connection errors.

Smithery.ai Integration for Unity AI MCP Server

Smithery.ai Integration for Unity AI MCP Server

Here's a translation of "A clean implementation of Smithery.ai integration for Unity AI MCP Server" into Chinese, along with a few options depending on the nuance you want to convey: **Option 1 (Most Literal and General):** * **中文:** 一个干净的 Smithery.ai 集成,用于 Unity AI MCP 服务器。 * **Pinyin:** Yī gè gānjìng de Smithery.ai jíchéng, yòng yú Unity AI MCP fúwùqì. * **Explanation:** This is a straightforward translation. "干净的 (gānjìng de)" means "clean" in the sense of being well-organized and free of unnecessary complexity. "集成 (jíchéng)" means "integration." **Option 2 (Emphasizing Efficiency and Elegance):** * **中文:** 一个简洁高效的 Smithery.ai 集成,适用于 Unity AI MCP 服务器。 * **Pinyin:** Yī gè jiǎnjié gāoxiào de Smithery.ai jíchéng, shìyòng yú Unity AI MCP fúwùqì. * **Explanation:** This option uses "简洁高效 (jiǎnjié gāoxiào)" which means "concise and efficient." This implies not only cleanliness but also good performance. "适用于 (shìyòng yú)" means "suitable for" or "applicable to." **Option 3 (Focusing on Well-Structured Code):** * **中文:** 一个结构清晰的 Smithery.ai 集成,用于 Unity AI MCP 服务器。 * **Pinyin:** Yī gè jiégòu qīngxī de Smithery.ai jíchéng, yòng yú Unity AI MCP fúwùqì. * **Explanation:** This option uses "结构清晰 (jiégòu qīngxī)" which means "clearly structured." This emphasizes the code's organization and readability. **Option 4 (More Technical, Emphasizing Best Practices):** * **中文:** 一个符合最佳实践的 Smithery.ai 集成,用于 Unity AI MCP 服务器。 * **Pinyin:** Yī gè fúhé zuìjiā shíjiàn de Smithery.ai jíchéng, yòng yú Unity AI MCP fúwùqì. * **Explanation:** This option uses "符合最佳实践 (fúhé zuìjiā shíjiàn)" which means "conforms to best practices." This is a more technical term often used in software development. **Which option is best depends on the context:** * If you want a general and easily understood translation, **Option 1** is a good choice. * If you want to emphasize the performance and efficiency of the integration, **Option 2** is better. * If you want to highlight the code's organization and readability, **Option 3** is preferable. * If you're targeting a technical audience and want to emphasize adherence to coding standards, **Option 4** is the most appropriate. Therefore, I recommend **Option 1** as the default, unless you have a specific reason to choose one of the others.

🌦️ Weather MCP Server

🌦️ Weather MCP Server

一个用于获取天气的 MCP 服务器,使用 Python 编写。

github-mcp-server-wheel

github-mcp-server-wheel

包裹 (bāo guǒ)

Stata MCP Server

Stata MCP Server

在 Stata 统计软件和代码编辑器(如 VS Code 和 Cursor)之间架起一座桥梁,使用户能够直接从编辑器运行 Stata 命令,实时查看输出,并获得 AI 驱动的 Stata 编码辅助。

Readwise MCP Server

Readwise MCP Server

A lightweight Python-based server that enables users to manage and retrieve their Readwise highlights and daily reviews through a token-efficient interface. It supports features like document importing, historical backfilling, and highlight searching with built-in deduplication and state management.

Verified Repo Memory MCP

Verified Repo Memory MCP

Provides repository-scoped safe memory for AI coding agents with just-in-time verification against file changes to ensure facts remain accurate. It links memories to specific code citations and automatically marks them as stale if the underlying source code is modified or deleted.

biostudies-mcp-server

biostudies-mcp-server

Backlog MCP Server

Backlog MCP Server

A Model Context Protocol server that enables Claude to interact with Backlog project management tools through API integration, allowing management of projects, issues, wiki pages and other Backlog resources.

BC Calculator MCP Server

BC Calculator MCP Server

Provides arbitrary precision arithmetic operations and advanced mathematical computations through the Unix bc calculator, supporting complex expressions, mathematical functions, and multi-line scripts with configurable precision.

Todoist Python MCP Server

Todoist Python MCP Server

一个模型上下文配置文件服务器,使 Claude 能够与 Todoist 交互,允许用户通过自然语言命令创建、检索、更新和管理任务。

MCP Thought Server

MCP Thought Server

一个强大的服务器,通过模型上下文协议(MCP)提供高级思维工具,以增强像 Cline 这样的人工智能代理的推理、规划和迭代改进能力。

AzureDevOpsMCP

AzureDevOpsMCP

一个概念验证的 MCP 服务器,可以查询 Azure DevOps。 (Yī gè gàiniàn yànzhèng de MCP fúwùqì, kěyǐ cháxún Azure DevOps.)

Card Magic MCP

Card Magic MCP

Implements the Chico & Dico card magic trick by encoding a hidden fifth card within the specific arrangement of four cards. It provides tools to both encode five-card sets into sequences and decode those sequences to reveal the hidden card.

Sentry MCP Server

Sentry MCP Server

A stateless FastMCP server that enables interaction with multiple Sentry instances, including US, EU, and self-hosted versions, through a single deployment. It provides tools for searching issues, events, and traces, allowing users to monitor and debug applications using natural language.

MCP AI POC

MCP AI POC

Provides AI-powered development tools including code generation, refactoring, debugging, performance optimization, and test generation, along with smart prompts for code analysis and documentation, and a built-in knowledge base of coding best practices.

Playwright MCP Extension Repro

Playwright MCP Extension Repro

A minimal reproduction repository designed to demonstrate and test Chrome extension loading within the Playwright MCP server. It evaluates specific configuration settings required for successful extension injection and page modification.

prayer_time MCP Server

prayer_time MCP Server

一个 MCP 服务器,提供每日五次萨拉特(礼拜 | 祈祷)的时间,以及午夜、日落和日出的时间。

MCP Knowledge Base Server

MCP Knowledge Base Server

A local document processing server that can index various document formats (PDF, DOCX, TXT, HTML) and answer questions based on their content using the Model Context Protocol.

RabbitMQ MCP Server

RabbitMQ MCP Server

镜子 (jìng zi)

Flashcard MCP

Flashcard MCP

Enables users to create, review, and manage flashcards using the SM-2 spaced repetition algorithm for optimized learning. It supports organizing cards into projects and automatically handles review scheduling based on user performance.

Proton Drive MCP

Proton Drive MCP

A Model Context Protocol server that enables AI assistants to interact with Proton Drive files, supporting operations like listing, reading, creating, and deleting files and folders.

NWS Weather MCP Server

NWS Weather MCP Server

Provides weather alerts for US states and geographic forecasts by leveraging the National Weather Service (NWS) API. It is built with Node.js and TypeScript, featuring a layered architecture and Zod-based input validation.

MCP Server Manager

MCP Server Manager

镜子 (jìng zi)

MCP Context Provider

MCP Context Provider

Provides persistent tool context that survives across Claude Desktop chat sessions, automatically injecting tool-specific rules, syntax preferences, and best practices. Eliminates the need to re-establish context in each new conversation.