发现优秀的 MCP 服务器

Uber MCP Server

Enables AI assistants to interact with the Uber API for ride management, including requesting rides, obtaining price and time estimates, and tracking active trip status. It supports comprehensive journey features such as viewing ride history, cancelling requests, and rating drivers through a secure OAuth 2.0 integration.

Dangerous MCP

一个演示服务器，通过访问敏感环境变量来揭示安全风险，说明 MCP 工具如何在未经明确同意的情况下潜在地泄露用户数据。

Dockerized GitHub MCP Server

这是本地的 MCP 服务器。 (Zhè shì běndì de MCP fúwùqì.)

hello-mcp-server-current-time

好的，这是一个基于 `spring-ai-starter-mcp-server` 的自定义 MCP Server 简单示例，用于获取当前时间。 我将提供代码示例，并解释关键部分。 **1. 项目结构 (假设 Maven 项目)** ``` my-mcp-server/ ├── pom.xml └── src/ └── main/ ├── java/ │ └── com/example/ │ └── mcp/ │ ├── config/ │ │ └── McpServerConfig.java // MCP Server 配置 │ └── controller/ │ └── TimeController.java // 处理时间请求的 Controller └── resources/ └── application.properties // 配置文件 ``` **2. `pom.xml` (Maven 依赖)** ```xml <?xml version="1.0" encoding="UTF-8"?> <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd"> <modelVersion>4.0.0</modelVersion> <parent> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-parent</artifactId> <version>3.2.0</version> <!-- 使用最新的 Spring Boot 版本 --> <relativePath/> <!-- lookup parent from repository --> </parent> <groupId>com.example</groupId> <artifactId>my-mcp-server</artifactId> <version>0.0.1-SNAPSHOT</version> <name>my-mcp-server</name> <description>Demo project for Spring Boot MCP Server</description> <properties> <java.version>17</java.version> <spring-ai.version>1.0.0-M2</spring-ai.version> </properties> <dependencies> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-web</artifactId> </dependency> <dependency> <groupId>org.springframework.ai</groupId> <artifactId>spring-ai-core</artifactId> <version>${spring-ai.version}</version> </dependency> <dependency> <groupId>org.springframework.ai</groupId> <artifactId>spring-ai-spring-boot-starter-mcp-server</artifactId> <version>${spring-ai.version}</version> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-test</artifactId> <scope>test</scope> </dependency> </dependencies> <build> <plugins> <plugin> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-maven-plugin</artifactId> </plugin> </plugins> </build> </project> ``` **关键依赖:** * `spring-boot-starter-web`: 提供 Spring Web MVC 功能，用于创建 RESTful API。 * `spring-ai-core`: Spring AI 核心库。 * `spring-ai-spring-boot-starter-mcp-server`: Spring AI MCP Server 启动器。 **3. `application.properties` (配置文件)** ```properties # 端口号 server.port=8080 # MCP Server 配置 (可选，使用默认值即可) spring.ai.mcp.server.enabled=true spring.ai.mcp.server.path=/mcp ``` **4. `McpServerConfig.java` (MCP Server 配置)** ```java package com.example.mcp.config; import org.springframework.context.annotation.Configuration; import org.springframework.context.annotation.Bean; import org.springframework.ai.autoconfigure.AiServiceProperties; import org.springframework.ai.autoconfigure.McpServerProperties; import org.springframework.ai.mcp.server.AiServiceHandlerFunction; import org.springframework.ai.mcp.server.McpServerEndpoint; import org.springframework.ai.mcp.server.McpServerFunctionRegistry; import org.springframework.ai.mcp.server.support.DefaultMcpServerFunctionRegistry; import org.springframework.boot.autoconfigure.condition.ConditionalOnMissingBean; import org.springframework.context.ApplicationContext; import org.springframework.web.servlet.function.RouterFunction; import org.springframework.web.servlet.function.ServerResponse; import java.util.List; import static org.springframework.web.servlet.function.RouterFunctions.route; import static org.springframework.web.servlet.function.RequestPredicates.POST; @Configuration public class McpServerConfig { @Bean @ConditionalOnMissingBean public McpServerFunctionRegistry mcpServerFunctionRegistry() { return new DefaultMcpServerFunctionRegistry(); } @Bean public McpServerEndpoint mcpServerEndpoint(McpServerProperties mcpServerProperties, McpServerFunctionRegistry mcpServerFunctionRegistry, ApplicationContext applicationContext, List<AiServiceHandlerFunction> aiServiceHandlerFunctions) { return new McpServerEndpoint(mcpServerProperties, mcpServerFunctionRegistry, applicationContext, aiServiceHandlerFunctions); } @Bean public RouterFunction<ServerResponse> timeRouterFunction(TimeController timeController, McpServerProperties mcpServerProperties) { return route(POST(mcpServerProperties.getPath() + "/time"), timeController::getTime); } } ``` **5. `TimeController.java` (处理时间请求的 Controller)** ```java package com.example.mcp.controller; import org.springframework.stereotype.Component; import org.springframework.web.servlet.function.ServerRequest; import org.springframework.web.servlet.function.ServerResponse; import java.time.LocalDateTime; import java.time.format.DateTimeFormatter; import static org.springframework.web.servlet.function.ServerResponse.ok; @Component public class TimeController { public ServerResponse getTime(ServerRequest request) { LocalDateTime now = LocalDateTime.now(); DateTimeFormatter formatter = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss"); String formattedDateTime = now.format(formatter); return ok().body(formattedDateTime); } } ``` **解释:** * `@Component`: 将 `TimeController` 标记为一个 Spring 组件，使其可以被自动注入。 * `getTime(ServerRequest request)`: 处理 `/mcp/time` POST 请求的方法。 * `LocalDateTime.now()`: 获取当前时间。 * `DateTimeFormatter`: 格式化时间为 `yyyy-MM-dd HH:mm:ss` 格式。 * `ok().body(formattedDateTime)`: 返回 HTTP 200 OK 状态码，并将格式化后的时间作为响应体。 **6. 启动应用程序** 运行 Spring Boot 应用程序。 **7. 测试** 使用 `curl` 或 Postman 等工具发送 POST 请求到 `/mcp/time`： ```bash curl -X POST http://localhost:8080/mcp/time ``` **预期响应:** ``` 2023-11-21 10:30:00 (实际时间会不同) ``` **总结:** 这个示例展示了如何使用 `spring-ai-starter-mcp-server` 创建一个简单的 MCP Server，并添加自定义的端点来处理特定的请求。 关键步骤包括： 1. 添加必要的 Maven 依赖。 2. 配置 `application.properties`。 3. 创建一个 Controller 来处理请求。 4. 创建一个配置类，将Controller注册到RouterFunction中。 5. 启动应用程序并测试端点。 **重要提示:** * 确保你已经安装了 Java 17 或更高版本。 * 根据你的实际需求调整时间格式。 * 这个示例非常简单，你可以根据需要添加更复杂的功能，例如身份验证、授权、数据验证等。 * 请根据实际情况调整 Spring AI 的版本号。 * 如果遇到问题，请检查日志文件以获取更多信息。 这个例子应该能帮助你开始构建自己的自定义 MCP Server。 如果你有任何问题，请随时提出。

Homelab MCP Server

Manage Docker infrastructure across multiple homelab hosts including Unraid, Proxmox, and bare metal servers. Enables container lifecycle management, log retrieval, resource monitoring, and Docker operations across your entire homelab from a single interface.

Cloud SQL Admin MCP Server

An MCP Server that enables interaction with Google Cloud SQL Admin API, allowing users to manage Cloud SQL database instances through natural language commands.

My Awesome MCP

A basic MCP server template built with FastMCP framework that provides example tools for echoing messages and retrieving server information. Serves as a starting point for building custom MCP servers with both stdio and HTTP transport support.

Chargebee MCP Server

A server that integrates with AI-powered code editors to provide immediate answers about Chargebee products and API services, offering context-aware code snippets and access to Chargebee's knowledge base.

Port MCP Server

镜子 (jìng zi)

YouTube MCP Server

能够与 YouTube 视频互动，通过提取元数据、多种语言的字幕，并将内容转换为带有各种模板的 Markdown 格式。

Keywords Everywhere MCP Server

A Model Context Protocol server that provides access to the Keywords Everywhere API, enabling AI assistants to perform SEO research including keyword analysis, domain traffic metrics, and backlink data.

mcp-audio-analysis

MCP 用于分析本地音频文件。

MCP Hardware Access Library

A Python framework that enables secure hardware control through the Model Context Protocol, allowing AI agents and automation systems to interact with physical devices across multiple platforms.

Instagram MCP Server

Enables interaction with Instagram API functionality through a FastMCP-based server. Provides type-safe access to Instagram features with comprehensive error handling and multiple authentication methods.

WordPress MCP Server

A server that enables integration between Claude Desktop and WordPress, allowing for AI-assisted blogging through a Message Control Protocol implementation.

CODING DevOps MCP Server

实现了模型上下文协议（MCP），通过标准化接口与 CODING DevOps 平台进行交互，以管理项目和工作项。

MCP Calculator Project

A communication pipe and tool suite that enables AI models to interact with external systems through mathematical calculations, remote control, and data processing. It supports multiple transport protocols including stdio, SSE, and HTTP for flexible and extensible tool integration.

Akash MCP Server

一个实现了模型上下文协议的 TypeScript 服务器，它使 AI 代理能够与 Akash 网络交互，允许它们通过类型化的工具部署应用程序、创建租约、管理部署以及访问其他 Akash 服务。

HashiCorp Vault MCP Server

Enables language models to securely manage HashiCorp Vault secrets and ACL policies through the Model Context Protocol. It supports automated secret rotation, discovery, and HCL policy authoring using a suite of dedicated tools and resources.

Time-MCP

An agentic AI system that answers time-related questions by calling a time API tool and general questions using an LLM, accessible through a simple chat interface.

react-analyzer-mcp

* 在本地分析你的 React 项目 * 使用 AST 解析 + AI 实现一致的输出 * 一次性为你的 React 代码创建 Markdown 文档和 llm.txt 文件

Sample MCP Server

A TypeScript-based MCP server implementing a simple notes system that allows users to create, access, and generate summaries of text notes.

Salesforce MCP

Enables interaction with Salesforce API using jsforce, allowing users to query and manage Salesforce data through the Model Context Protocol with username/password authentication.

Zhihu MCP Server

A Model Context Protocol server that enables users to automatically generate articles using large language models and publish them directly to Zhihu (a Chinese Q\&A platform).

Netmex MCP

A lightweight and extendable MCP server toolkit that allows developers to build and integrate custom tools with AI assistants through automatic tool discovery from local directories or npm packages.

Python MCP Sandbox

一个交互式的 Python 代码执行环境，允许用户和大型语言模型 (LLM) 在隔离的 Docker 容器中安全地执行 Python 代码并安装软件包。

Github MCP Server

镜子 (jìng zi)

Placeholder Image Generator

Generates customizable placeholder images with configurable dimensions, colors, and text using HTML5 Canvas. Supports multiple formats (PNG/JPEG) with automatic text scaling and contrast detection.

Playwright Accessibility Testing MCP Server

Enables comprehensive WCAG 2.0/2.1 accessibility testing of web applications using Playwright and axe-core. Supports natural language element finding, auto-discovery of interactive components, and generates detailed compliance reports with screenshots.