A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. Enables LLMs to interact with web pages through structured accessibility snapshots without vision models. Requires Node.js 18 or newer. Configuration file path can be specified via the --config option.

MCP server for Context7 that provides up-to-date, version-specific documentation and code examples for libraries directly into your prompt. Requires Node.js >= v18.0.0 runtime.

MCP server for advanced web search using Tavily, providing search, extract, map, and crawl tools with real-time web search and intelligent data extraction capabilities.

MCP server for Firecrawl web scraping integration. Supports both cloud and self-hosted instances. Features include web scraping, batch processing, structured data extraction, and LLM-powered content analysis. Requires FIRECRAWL_API_KEY environment variable for API access. Optional FIRECRAWL_API_URL for self-hosted instance configuration.

A Model Context Protocol server for generating charts using AntV. This is a TypeScript-based MCP server that provides chart generation capabilities. It allows you to create various types of charts through MCP tools.

BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation. Requires Blender 3.0+ and Python 3.10+. The uv package manager must be installed separately as per instructions.

Universal AI bridge for Obsidian vaults using the Model Context Protocol (MCP) standard. Connect any MCP-compatible AI assistant to your knowledge base. Requires a local Obsidian vault directory path provided as an argument.

A Model Context Protocol (MCP) server for interacting with Bugsnag. This server allows LLM tools like Cursor and Claude to investigate and resolve issues in Bugsnag. Requires a Bugsnag API key configured via the BUGSNAG_API_KEY environment variable.

MCP server for Chrome DevTools that lets your coding agent control and inspect a live Chrome browser for automation, debugging, and performance analysis. Requires Node.js 22+ and a current stable Chrome browser.

A lightweight MCP server for semantic memory storage, knowledge graphs, conversational recall, and cross-session context. Supports persistent storage with SQLite and optional cloud sync (S3, R2, D1). Configuration via environment variables for database paths and cloud credentials.

Model Context Protocol server for Figma integration. Requires a Figma API access token to be set via environment variable or command line argument.

Model Context Protocol (MCP) server that provides comprehensive SQLite database interaction capabilities. Requires a local SQLite database file path to be provided as a command line argument.

一组用于模型上下文协议（MCP）的参考实现，展示了对大型语言模型（LLM）工具和数据源的安全且受控的访问方式。

一种将存储库内容打包成单一文件以供AI使用的工具。会在当前目录生成一个 repomix-output.xml 文件。无需外部数据文件。

Qwen-Agent 是一个用于开发基于 Qwen 的大规模语言模型（LLM）应用程序的框架，支持指令遵循、工具使用、规划和记忆功能。包括示例应用如浏览器助手、代码解释器和自定义助手。使用阿里云 DashScope 模型服务时，需设置环境变量 DASHSCOPE_API_KEY。

FastMCP is a fast, Pythonic framework to build MCP servers and clients. It requires Python 3.10 or higher. No external data files are required by default.

Zen MCP is a Model Context Protocol server that orchestrates multiple AI models including Claude, Gemini, O3, and others for enhanced code analysis, problem-solving, and collaborative development. It requires API keys for external AI providers configured via environment variables such as GEMINI_API_KEY, OPENAI_API_KEY, and OPENROUTER_API_KEY. Custom model aliases can be configured in conf/custom_models.json.

Chrome MCP Server 是一个基于 Chrome 扩展的模型上下文协议（MCP）服务器，能够将您的 Chrome 浏览器功能暴露给像 Claude 这样的 AI 助手，实现复杂的浏览器自动化、内容分析和语义搜索。需要安装 Chrome 扩展和全局安装 mcp-chrome-bridge npm 包。

MCP server that streams hand-drawn Excalidraw diagrams with smooth viewport camera control and interactive fullscreen editing.

MCP server for building bots on the Post Fiat (PFTL) network that enables encrypted on-chain messaging and bot interactions. Configuration requires copying mcp.json.example to your LLM client's MCP config location. Environment variables like BOT_SEED are used for wallet seed configuration.

MCP server to access OpenViking context DB from Claude Code. Requires OpenViking server running at localhost:1933 and Python 3.10+. Requires a local .mcp.json config file to specify server command and environment variables.

MCP server for browser automation with anti-detection. Scout pages, find elements, interact with websites, and monitor network traffic. Supports environment variable configuration via a .env file for credentials and settings.

MCP server that lets Claude query Grok as a quorum peer for architecture debates, code review, and multi-agent reasoning. Requires an xAI API key configured via environment variable XAI_API_KEY or a key file at ~/.xai_api_key.

Read-only MCP server that exposes NORA Dashboard data from Upstash Redis. Requires environment variables for Upstash Redis credentials configured via .env file or environment variables.