Chrome MCP Server — AI Agent 浏览器自动化与 DevTools
安装 Chrome MCP 服务器，让 AI Agent 完全控制浏览器——导航页面、提取内容、执行 JavaScript、操作 DevTools、自动化 Web 工作流。多种实现适配不同场景。
安装 Chrome MCP Server
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-puppeteer"]
}
}
}Chrome MCP Proxy
CDP proxy for Chrome DevTools MCP — persistent connection, multi-agent isolation, anti-focus-stealing. Built for Claude Code.
Chrome MCP Background Proxy — Fix Popups, Focus Stealing & Multi-Agent Conflicts
Drop-in proxy for Chrome MCP. Solves Chrome 146+ debugging popups, focus stealing, and multi-agent conflicts with persistent CDP connection, request ID remapping, and sessionId-based event routing.
Chrome DevTools MCP — Browser Debugging for AI Agents
Give your AI coding agent full access to Chrome DevTools for browser automation, debugging, and performance analysis. Works with Claude, Cursor, Copilot, and 15+ AI tools.
Claude Code Templates — 600+ Agents, Commands & MCPs
Ready-to-use Claude Code configurations: 600+ agents, 200+ commands, 55+ MCPs, and project templates. Install any template with one command.
Jina Reader — AI-Friendly Web Content Extraction
Convert any URL to clean markdown for AI consumption. Free API at r.jina.ai strips ads, navigation, and clutter. Used by AI agents for web research and RAG.
Google Stitch MCP — AI Design via Model Context Protocol
Connect Claude Code, Cursor, Gemini CLI, or VS Code to Google Stitch for AI-driven UI design. Create projects, generate screens from text, edit designs, manage design systems — all via MCP.
Pal MCP Server — Multi-Model AI Gateway for Claude Code
MCP server that lets Claude Code use Gemini, OpenAI, Grok, and Ollama as a unified AI dev team. Features model routing, CLI-to-CLI bridge, and conversation continuity across 7+ providers.
Neon — Serverless Postgres with Database Branching
Serverless PostgreSQL with instant database branching, autoscaling, and a generous free tier. Branch your database like git branches — test schema changes without touching production. 16,000+ stars.
Codebase Memory MCP — Code Intelligence for AI Agents
High-performance code intelligence MCP server. Indexes repos in milliseconds via tree-sitter AST, supports 66 languages, sub-ms graph queries. MIT, 1,300+ stars.
Codebase Memory MCP — Code Knowledge Graph Server
High-performance MCP server that indexes codebases into persistent knowledge graphs. Supports 66 languages, sub-millisecond queries, and claims 99% fewer tokens than raw file context. 1,100+ stars.
Appwrite — Open-Source Backend for AI Apps
Complete cloud backend with auth, database, storage, functions, and messaging in one platform. Self-hostable. 55K+ GitHub stars.
Neon MCP — Serverless Postgres via AI Agents
MCP server for Neon serverless Postgres. Create projects, branch databases, run SQL, optimize queries via natural language. Safe migration workflow with branching. MIT, 574+ stars.
LMDeploy — High-Performance LLM Deployment Toolkit
Deploy and serve LLMs with 1.8x higher throughput than vLLM. 4-bit quantization, OpenAI-compatible API. By InternLM. 7.7K+ stars.
MCPHub — Centralized MCP Server Management Hub
Manage multiple MCP servers from one dashboard. Smart routing, hot-swap config, OAuth 2.0 auth. Deploy via Docker in one command. Apache-2.0, 2,000+ stars.
Wrangler MCP — Cloudflare Workers for AI Agents
MCP server for managing Cloudflare Workers, KV, R2, and D1 from AI agents. Deploy serverless functions, manage storage, and query databases through Claude Code tool calls.
Best of MCP Servers — 450 Ranked MCP Servers
A weekly-updated ranked directory of 450 MCP servers across 34 categories with quality scores based on GitHub stars, contributors, and activity. Find the best MCP server for any use case.
Smithery CLI — MCP Server Registry & Installer
Search, install, and manage MCP servers from Smithery's registry of 6,000+ servers. One command to connect any MCP server to Claude, Cursor, or other AI tools. AGPL-3.0.
Firecrawl MCP — Web Scraping Server for AI Agents
Official Firecrawl MCP server for AI agents to scrape, crawl, and extract structured data from any website. Supports batch scraping, search, and markdown extraction. 15,000+ stars.
Uptime Kuma — Self-Hosted Uptime Monitoring
Monitor HTTP, TCP, DNS, Docker services with notifications to 90+ channels. Beautiful dashboard. 84K+ GitHub stars.
Browser Use — AI Agent Browser Automation
Let AI agents control web browsers with natural language. Browser Use provides vision-based element detection, multi-tab support, and works with any LLM provider.
PostgreSQL MCP Server — Database Queries for AI
MCP server for PostgreSQL database access. Run read-only SQL queries, inspect schemas, list tables, and analyze data directly from Claude Code or Cursor.
MCP Inspector — Debug MCP Servers Visually
Official MCP Inspector for testing and debugging MCP servers. 9.3K+ stars. Web UI, tool/resource/prompt inspection, request testing.
Context7 — Up-to-Date Docs MCP for AI Editors
MCP server that provides AI code editors with up-to-date library documentation. Eliminates hallucinations from outdated training data. Supports 1000+ libraries. 51K+ stars.
Engram — Persistent Memory System for AI Agents
Agent-agnostic persistent memory system with SQLite full-text search. Ships as MCP server, HTTP API, CLI, and TUI. Gives any AI coding agent long-term memory across sessions. 2,300+ stars.
mcp-agent — Build AI Agents with MCP Patterns
mcp-agent is a Python framework for building AI agents using the Model Context Protocol. 8.2K+ GitHub stars. Implements composable workflow patterns (orchestrator, map-reduce, evaluator-optimizer, rou
Notion MCP — Connect AI Agents to Your Knowledge Base
Official MCP server for Notion workspace access. Search pages, read content, create and update databases, and manage tasks in Notion through Claude Code tool calls.
Context7 — Live Library Docs for LLMs, 51K Stars
MCP server fetching up-to-date, version-specific library documentation into LLM context. Eliminates hallucinated APIs across 30+ AI coding tools.
Unstructured — Document ETL for LLM Pipelines
Extract clean data from PDFs, DOCX, HTML, images, and emails for RAG and LLM ingestion. 14K+ GitHub stars.
Serena — Semantic Code Agent via MCP
Serena is a coding agent MCP server with semantic code retrieval and editing. 22K+ stars. Understands classes, functions, symbols for precise context-aware edits. MIT.
Glama — MCP Server Discovery and Management
Directory and management platform for MCP servers. Discover, install, and monitor Model Context Protocol servers for Claude Code, Cline, and other AI coding tools.
AI Agent 的完整浏览器控制
The Chrome MCP server ecosystem gives AI agents the ability to see and interact with the web. There are multiple implementations optimized for different workflows: Puppeteer MCP (headless automation — scraping, testing, screenshots), Chrome DevTools MCP (connect to your live browser session for debugging), and Chrome MCP Proxy (background operation without focus-stealing popups).
For developers, the most transformative use case is AI-assisted debugging. Point the DevTools MCP at your running app, describe the bug, and the agent can inspect the DOM, read console errors, check network requests, analyze performance profiles, and suggest fixes — all without you touching the Chrome inspector. For QA teams, Puppeteer MCP enables AI-driven test generation: the agent navigates your app, identifies interactive elements, and writes end-to-end tests.
For web scraping and data extraction, Chrome MCP servers handle JavaScript-heavy sites that static scrapers can't reach. The agent can navigate SPAs, wait for dynamic content, extract structured data, and handle pagination. Browse the full browser automation tools directory for Playwright alternatives, and see web scraping tools for complementary extraction frameworks. For testing workflows, check AI testing tools on TokRepo.
The web is the world's largest API. Chrome MCP is how AI agents call it.
常见问题
What Chrome MCP servers are available?+
Three main options: (1) Puppeteer MCP (@modelcontextprotocol/server-puppeteer) — headless Chrome for automation, scraping, and testing. (2) Chrome DevTools MCP — connects to a running Chrome instance via the DevTools Protocol for live debugging. (3) Chrome MCP Proxy — runs Chrome in the background without focus-stealing, ideal for long-running agent tasks. Choose based on your use case.
Which Chrome MCP should I install first?+
Start with Puppeteer MCP — it's the official reference implementation, requires zero setup (downloads its own Chromium), and handles the most common use cases: navigating pages, taking screenshots, extracting content, filling forms, and clicking elements. Upgrade to DevTools MCP only if you need to debug a live browser session.
Can Chrome MCP handle JavaScript-heavy single-page apps?+
Yes. Unlike static HTTP scrapers, Chrome MCP runs a real browser engine. It executes JavaScript, renders React/Vue/Angular apps, waits for API calls to complete, and interacts with the fully rendered DOM. The agent can wait for specific elements to appear, handle infinite scroll, and navigate client-side routing.
Does it work with sites that require login?+
Yes. The agent can fill login forms, handle OAuth redirects, and maintain cookies across page navigations. For DevTools MCP connected to your real browser, it uses your existing session — no login needed. For Puppeteer, you can pass cookies or have the agent log in at the start of each session. Avoid storing credentials in MCP configs — use environment variables.
Can AI agents write browser tests with Chrome MCP?+
Yes. A common pattern: install Puppeteer MCP, point the agent at your app URL, and ask it to 'write end-to-end tests for the checkout flow.' The agent navigates the app, identifies forms and buttons, writes Playwright or Puppeteer test scripts, and can even run them to verify they pass. Much faster than writing browser tests manually.