Discover Awesome MCP Servers
Extend your agent with 28,665 capabilities via MCP servers.
- All28,665
- Developer Tools3,867
- Search1,714
- Research & Data1,557
- AI Integration Systems229
- Cloud Platforms219
- Data & App Analysis181
- Database Interaction177
- Remote Shell Execution165
- Browser Automation147
- Databases145
- Communication137
- AI Content Generation127
- OS Automation120
- Programming Docs Access109
- Content Fetching108
- Note Taking97
- File Systems96
- Version Control93
- Finance91
- Knowledge & Memory90
- Monitoring79
- Security71
- Image & Video Processing69
- Digital Note Management66
- AI Memory Systems62
- Advanced AI Reasoning59
- Git Management Tools58
- Cloud Storage51
- Entertainment & Media43
- Virtualization42
- Location Services35
- Web Automation & Stealth32
- Media Content Processing32
- Calendar Management26
- Ecommerce & Retail18
- Speech Processing18
- Customer Data Platforms16
- Travel & Transportation14
- Education & Learning Tools13
- Home Automation & IoT13
- Web Search Integration12
- Health & Wellness10
- Customer Support10
- Marketing9
- Games & Gamification8
- Google Cloud Integrations7
- Art & Culture4
- Language Translation3
- Legal & Compliance2
MCP Registry Server
Enables searching and retrieving detailed information about MCP servers from the official MCP registry. Provides tools to list servers with filtering options and get comprehensive details about specific servers.
MCP Gemini API Server
MCPプロトコルを通じて、テキスト生成、画像分析、YouTube動画分析、ウェブ検索機能など、Google Gemini AIの機能へのアクセスを提供するサーバー。
Simple MCP Server
了解了。以下是用极简代码演示如何构建 MCP (Mesh Configuration Protocol) Server 的示例,并附带一些解释。请注意,这只是一个非常基础的示例,用于说明 MCP 的核心概念。实际的 MCP Server 实现会更加复杂,需要处理更多细节,例如身份验证、授权、错误处理、版本控制等。 ```python # 导入必要的库 (这里我们使用 gRPC) import grpc from concurrent import futures # 假设你已经定义了 MCP 的 protobuf 定义 (例如,mcp.proto) # 并使用 `protoc` 生成了 Python 代码 # 例如: # protoc -I. --python_out=. mcp.proto # 导入生成的 protobuf 代码 import mcp_pb2 import mcp_pb2_grpc # 定义一个简单的 MCP 服务 class McpService(mcp_pb2_grpc.AggregatedDiscoveryServiceServicer): def StreamAggregatedResources(self, request_iterator, context): """ 处理来自客户端的资源请求流。 """ for request in request_iterator: print(f"Received request: {request}") # 在这里,你需要根据请求的内容,从你的数据源获取相应的资源。 # 为了简化,我们这里返回一个空的响应。 response = mcp_pb2.AggregatedDiscoveryResponse( version_info="1", # 资源的当前版本 resources=[], # 返回的资源列表 (这里为空) type_url=request.type_url, # 资源类型 URL nonce="some-nonce" # 用于跟踪请求/响应的 nonce ) yield response # 创建 gRPC 服务器 def serve(): server = grpc.server(futures.ThreadPoolExecutor(max_workers=10)) mcp_pb2_grpc.add_AggregatedDiscoveryServiceServicer_to_server(McpService(), server) server.add_insecure_port('[::]:50051') # 监听所有接口的 50051 端口 server.start() print("MCP Server started, listening on port 50051") server.wait_for_termination() if __name__ == '__main__': serve() ``` **代码解释:** 1. **导入必要的库:** - `grpc`: gRPC 库,用于构建 gRPC 服务。 - `concurrent.futures`: 用于创建线程池,处理并发请求。 - `mcp_pb2` 和 `mcp_pb2_grpc`: 从你的 `mcp.proto` 文件生成的 Python 代码。 你需要先定义 MCP 的 protobuf 定义,然后使用 `protoc` 编译器生成这些文件。 2. **定义 MCP 服务 (`McpService`):** - 继承 `mcp_pb2_grpc.AggregatedDiscoveryServiceServicer` 类,这是 gRPC 为 MCP 服务生成的基类。 - 实现 `StreamAggregatedResources` 方法。 这是 MCP Server 必须实现的唯一方法。 它处理来自客户端的资源请求流。 - 在 `StreamAggregatedResources` 方法中: - 循环遍历客户端发送的每个请求 (`request_iterator`)。 - 打印接收到的请求 (用于调试)。 - **关键部分:** 根据 `request.type_url` (资源类型) 和其他请求参数,从你的数据源 (例如数据库、配置文件、API 等) 获取相应的资源。 **这个示例中,我们为了简化,直接返回一个空的资源列表。** - 创建一个 `AggregatedDiscoveryResponse` 对象,包含: - `version_info`: 资源的当前版本。 - `resources`: 返回的资源列表。 - `type_url`: 资源类型 URL (与请求中的 `type_url` 相同)。 - `nonce`: 一个随机字符串,用于跟踪请求/响应。 - 使用 `yield` 关键字返回响应。 因为 `StreamAggregatedResources` 是一个流式方法,所以需要使用 `yield` 来逐个返回响应。 3. **创建 gRPC 服务器 (`serve` 函数):** - 创建一个 gRPC 服务器实例。 - 使用 `mcp_pb2_grpc.add_AggregatedDiscoveryServiceServicer_to_server` 将你的 `McpService` 实例注册到服务器。 - 使用 `server.add_insecure_port` 添加一个监听端口 (这里使用 50051 端口,并且是不安全的,仅用于演示)。 **在生产环境中,你应该使用 TLS 加密。** - 使用 `server.start` 启动服务器。 - 使用 `server.wait_for_termination` 等待服务器终止。 4. **运行服务器:** - `if __name__ == '__main__':` 确保只有在直接运行脚本时才执行 `serve` 函数。 **如何运行:** 1. **安装 gRPC:** ```bash pip install grpcio grpcio-tools protobuf ``` 2. **定义 `mcp.proto` 文件:** 创建一个名为 `mcp.proto` 的文件,并定义 MCP 的 protobuf 消息。 一个简单的例子: ```protobuf syntax = "proto3"; package envoy.service.discovery.v3; message AggregatedDiscoveryRequest { string version_info = 1; repeated string resource_names = 2; string type_url = 3; string response_nonce = 4; string error_detail = 5; // google.rpc.Status as JSON } message AggregatedDiscoveryResponse { string version_info = 1; repeated bytes resources = 2; // Any as bytes string type_url = 3; string nonce = 4; } service AggregatedDiscoveryService { rpc StreamAggregatedResources(stream AggregatedDiscoveryRequest) returns (stream AggregatedDiscoveryResponse) {} } ``` 3. **生成 Python 代码:** 使用 `protoc` 编译器从 `mcp.proto` 文件生成 Python 代码: ```bash python -m grpc_tools.protoc -I. --python_out=. --grpc_python_out=. mcp.proto ``` 这会生成 `mcp_pb2.py` 和 `mcp_pb2_grpc.py` 文件。 4. **运行 Python 脚本:** ```bash python your_script_name.py ``` **重要注意事项:** * **Protobuf 定义:** `mcp.proto` 文件是 MCP 的核心。 你需要根据你的需求定义正确的消息类型和服务。 上面的例子只是一个非常简化的版本。 你应该参考 MCP 的官方文档或 Envoy 的 xDS 文档来了解更详细的 protobuf 定义。 * **资源获取:** `StreamAggregatedResources` 方法中的资源获取逻辑是 MCP Server 的关键部分。 你需要根据 `request.type_url` 和其他请求参数,从你的数据源获取相应的资源,并将它们序列化为 `bytes` (通常使用 `google.protobuf.Any` 消息类型)。 * **错误处理:** 在实际的 MCP Server 中,你需要处理各种错误情况,例如无效的请求、资源不存在、数据源错误等。 * **身份验证和授权:** 为了安全起见,你需要对 MCP 客户端进行身份验证和授权,以防止未经授权的访问。 * **版本控制:** MCP 使用 `version_info` 字段来跟踪资源的版本。 你需要正确地管理资源的版本,并在响应中返回正确的 `version_info`。 * **Nonce:** `nonce` 字段用于跟踪请求/响应。 客户端应该在请求中包含一个随机的 `nonce`,服务器应该在响应中返回相同的 `nonce`。 这可以帮助客户端检测重复的响应或丢失的响应。 * **流式处理:** MCP 使用 gRPC 的流式 API,这意味着客户端和服务器可以双向发送和接收消息流。 这允许客户端动态地请求资源,并允许服务器推送更新的资源。 这个示例提供了一个基本的框架,你可以根据你的具体需求进行扩展和修改。 建议你阅读 MCP 和 xDS 的官方文档,以了解更多细节。
octodet-elasticsearch-mcp
Read/write Elasticsearch mcp server with many tools
Nextcloud MCP Server
Enables LLMs to interact with Nextcloud instances through 30 tools across Notes, Calendar, Contacts, Tables, and WebDAV file operations, featuring a powerful unified search system for finding files without exact paths.
Fermat MCP
A FastMCP server for mathematical computations, including numerical and symbolic calculations with NumPy and SymPy integration, as well as data visualization through Matplotlib.
LocalFS MCP Server
Provides sandboxed access to local filesystem operations including directory and file management, content search with glob and regex patterns, and binary file support with configurable safety limits.
UML-MCP: A Diagram Generation Server with MCP Interface
UML-MCP Server は、MCP (Model Context Protocol) に基づいた UML 図生成ツールです。自然言語による記述や、PlantUML、Mermaid、Kroki を直接記述することで、様々な種類の UML 図を生成できます。
Multi-Tenant PostgreSQL MCP Server
Enables read-only access to PostgreSQL databases with multi-tenant support, allowing users to query data, explore schemas, inspect table structures, and view function definitions across different tenant schemas safely.
Security Scanner MCP Server
Enables comprehensive security scanning of code repositories to detect secrets, vulnerabilities, dependency issues, and configuration problems. Provides real-time security checks and best practice recommendations to help developers identify and prevent security issues.
MCPMan
A Model Context Protocol server manager that acts as a proxy/multiplexer, enabling connections to multiple MCP servers simultaneously and providing JavaScript code execution with access to all connected MCP tools. Supports both stdio and HTTP transports with OAuth authentication, batch tool invocation, and dynamic server management.
WritBase
A control plane for AI agents and human supervisors. Persistent task registry with scoped permissions, inter-agent delegation, and full provenance — all accessible via MCP. Deploy on Supabase free tier in 3 commands.
symbolics-mcp
An MCP server that enables LLMs to evaluate Lisp expressions on a Symbolics Genera machine over TCP. It bridges JSON-RPC requests to the Genera environment to return evaluation results, stdout, and stderr.
MCP Atlassian
An MCP server that integrates with Jira and Confluence to enable AI-powered issue management, content search, and document creation. It supports both Cloud and on-premise deployments, allowing users to automate workspace tasks through natural language.
dryai-mcp-server
SSL Monitor MCP Server
Enables monitoring of domain registration information via WHOIS lookup and SSL certificate validity checking. Provides domain expiration dates, registrar details, certificate validity periods, and issuer information for website security monitoring.
SD Elements MCP Server
A Model Context Protocol server that provides SD Elements API integration, enabling LLMs to interact with SD Elements security development lifecycle platform.
Mermaid Grammar Inspector
A Model Context Protocol (MCP) server for validating Mermaid diagram syntax and providing comprehensive grammar checking capabilities
shipstatic
MCP server for Shipstatic — deploy and manage static sites from AI agents. Works with Claude Code, Cursor, VS Code Copilot, and any MCP-compatible client.
Stock Market Research Assistant
So I tried out this cool tool I saw in a LinkedIn post https://openapitools.com All you need is your API schema (OpenAPI/Swagger), and it automatically generates an MCP schema for you. You can then drop it straight into Claude Desktop (or Cursor, LangChain, etc.) and instantly start chatting with
deployhq-mcp-server
DeployHQ MCP Server
YouTube MCP Server
Enables AI models to interact with YouTube content including video details, transcripts, channel information, playlists, and search functionality through the YouTube Data API.
YouTube Transcript MCP Server
Enables AI assistants to fetch and analyze transcripts from YouTube videos using video IDs or URLs, with support for multiple language preferences.
GSAP-Animation-Generate
A comprehensive GSAP animation generation tool that offers AI-driven intent analysis, full API coverage, and production-ready animation modes, helping developers quickly create high-performance animations.
Chrome MCP Server
Transforms Chrome browser into an AI-controlled automation tool that allows AI assistants like Claude to access browser functionality, enabling complex automation, content analysis, and semantic search while preserving your existing browser environment.
DICOM/HL7/FHIR Interoperability MCP Server
Built by a healthcare IT engineer with 19 years of PACS/RIS/integration experience. Bridges DICOM, HL7v2, and FHIR — maps between standards, decodes vendor private tags (GE, Siemens, Philips), generates Mirth Connect channels, and explains integration patterns. 12 tools covering tag lookup, message parsing, cross-standard mapping, and channel generation.
Flippa MCP
Enables users to search, analyze, and evaluate online business listings on Flippa using AI-powered tools for valuation and market research. It provides detailed metrics, risk assessments, and comparable sales data without requiring an API key or account.
Kommo MCP Server
Enables integration with Kommo CRM to manage leads, add notes and tasks, update custom fields, and list pipelines. Supports multi-tenant authentication and includes an approval system for bulk operations.
CVE Checker for Node Modules
Enables checking npm packages for known security vulnerabilities using the OSV API before installation. Supports both single package checks and bulk vulnerability scanning for multiple packages at once.
signbee-mcp
Document signing for AI agents. Send markdown or PDF for two-party e-signing with a single tool call — handles PDF generation, email verification, and SHA-256 certified delivery.