Discover Awesome MCP Servers

MCP Calculator Server

一个简单的模型上下文协议服务器，提供基本的算术运算（加法、减法、乘法、除法）作为工具，供大型语言模型调用。

Extract-Antv-Topic

A model context protocol server designed for AI development and QA, providing AntV document context and code examples.

NestJS MCP Server

A demonstration implementation of Model Context Protocol (MCP) using NestJS framework, allowing developers to build MCP-compatible applications with playground testing capabilities.

MCP Component Review

Analyzes React component changes by performing structural analysis and generating visual diffs to identify pixel-level differences. It integrates with Figma to validate implementation compliance against design specifications and automates component reviews across git branches.

YouTube Transcript Server

一个模型上下文协议服务器，支持从 YouTube 视频中检索带有特定语言支持的文本稿。

MCP Goodnews

一个模型上下文协议服务器，它从 NewsAPI 获取并使用 Cohere LLM 情感分析对积极新闻文章进行排序，从而使用户能够通过诸如 Claude Desktop 等界面访问令人振奋的新闻报道。 (Alternative, slightly more literal translation): 一个模型上下文协议服务器，它使用 Cohere LLM 情感分析从 NewsAPI 获取并对积极的新闻文章进行排名，从而使用户能够通过像 Claude Desktop 这样的界面来访问令人鼓舞的新闻故事。

Python Memory MCP Server

A Python-based server providing persistent memory management for AI models with SQLite and Markdown dual backend storage. It features full-text search, RAG-enhanced querying, and cross-project knowledge sharing for integration with Claude, Cursor, and Rovo Dev.

nebulablock-mcp-server

This server integrates with the fastmcp library to expose the full range of NebulaBlock API functionalities as accessible tools, enabling seamless and efficient interaction within any MCP-compatible environment.

Financial Modeling Prep MCP Server

一个模型上下文协议（Model Context Protocol）服务器，它使像 Claude 这样的 AI 助手能够以编程方式访问来自 Financial Modeling Prep API 的金融数据，包括公司概况、财务报表、指标、美国证券交易委员会（SEC）文件和市场数据。

Federated Directory MCP

Enables contact searches within the Federated Directory system by name or email address. Provides comprehensive logging and automatic query type detection for seamless contact lookup integration.

HackerOne MCP Server

Provides read-only access to HackerOne reports, program scopes, and bounty earnings through the HackerOne API. It enables users to analyze hunting patterns, check asset eligibility, and retrieve report details or triage conversations via natural language.

Sequential Thinking Multi-Agent System (MAS)

镜子 (jìng zi)

SharePoint MCP Server

A lightweight MCP server that enables integration with Microsoft SharePoint, allowing clients to interact with documents and folders through the Model Context Protocol.

WireMCP

A Model Context Protocol server that provides LLMs with real-time network traffic analysis capabilities, enabling tasks like threat hunting, network diagnostics, and anomaly detection through Wireshark's tshark.

GitHub MCP Server

Enables interaction with GitHub repositories, issues, pull requests, and code search through natural language. Supports self-hosted deployment with built-in analytics and flexible authentication options.

Obsidian MCP Server

Enables AI assistants to interact with Obsidian vaults through direct filesystem access, supporting note management, lightning-fast search with SQLite indexing, image analysis, tag/link management, and bulk operations.

MCP MAGMA Handbook Server

Provides AI assistants with semantic search access to the MAGMA computational algebra system handbook, enabling natural language queries for documentation, code examples, and explanations of MAGMA syntax and mathematical functions.

MCPist

A gateway service that connects AI assistants to numerous external tools like Notion, GitHub, and Google Workspace through a single Model Context Protocol endpoint. It provides a centralized hub for managing multiple tool integrations with secure authentication and a unified API architecture.

Podman MCP Server

Enables AI tools to manage containerized applications through Podman, supporting container lifecycle operations, command execution, log viewing, image management, and resource monitoring. Features automatic network discovery for seamless integration with MCP Discovery Hub.

MCP MongoDB Server

一个模型上下文协议服务器，提供对 MongoDB 数据库的访问。该服务器使大型语言模型 (LLM) 能够检查集合模式并执行只读查询。

GraphQL MCP Toolkit

一个模型上下文协议服务器，它通过提供模式自省和查询执行能力，使大型语言模型（LLM）能够与 GraphQL API 进行交互。

TypeScript MCP Server Boilerplate

A template project for quickly building Model Context Protocol (MCP) servers using TypeScript and the official SDK. It includes pre-configured examples for tools and resources to help developers jumpstart their custom MCP server development.

Enterprise MCP Template

A production-ready framework for building enterprise-grade MCP servers featuring integrated OAuth 2.0 authentication and modular architectural patterns. It simplifies the creation of secure, standardized tools that allow AI assistants to interact with complex upstream platforms like Salesforce and NetSuite.

pg-mcp

PG-MCP 是一个 HTTP 服务器实现，它使 AI 系统能够通过 MCP 与 PostgreSQL 数据库进行交互，并提供查询、连接到多个数据库以及浏览模式资源的工具。该系统通过从数据库目录中提取表/列描述来丰富上下文。

VAP Media · Unified MCP Server for AI Agents (Flux · Veo · Suno)

Execution control layer for AI agents - Reserve, execute, burn/refund pattern for media generation

OpenRouter Agents MCP Server

一个模型上下文协议服务器，它使对话式大型语言模型能够将复杂的研究任务委托给由各种 OpenRouter 模型驱动的专业 AI 代理，并由 Claude 编排器进行协调。

RuneScape Wiki MCP Server

Enables access to RuneScape 3 data including real-time Grand Exchange prices, item information, historical price trends, and player statistics. Supports multiple game modes and provides comprehensive RuneScape Wiki API integration through natural language.

MCP Memory Server

A persistent local vector memory server that allows users to store and search project-specific context using LanceDB and local embeddings. It enables MCP-compliant editors to maintain long-term memory across different projects without requiring external API keys.

Git Commit Video Walkthrough Generator

Generates narrated video walkthroughs of git commits, staged/unstaged changes, or entire codebases with AI-powered analysis, syntax-highlighted code visualization, and text-to-speech narration.

MCP-RAG

MCP-RAG 服务器是模型上下文协议 (MCP) 的一个实现，旨在通过语义向量搜索为 AI 助手提供对相关文档的实时访问，从而增强其能力。它使 AI 模型能够检索和处理文档，从而生成基于最新信息的、具有上下文感知能力的响应。