ติดตั้ง MCP Chrome อย่างไร?

คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP

MCP Chrome ต้องใช้ API key ไหม?

ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น

MCP Chrome ใช้ทรานสปอร์ตแบบใด?

MCP Chrome ทำงานแบบโลคัลผ่าน stdio

MCP Chrome ถูกตรวจสอบล่าสุดเมื่อใด?

ตรวจสอบล่าสุดเมื่อ 2026-11-08 A New Visual Editor for Claude Code & Codex, for more detail here:. Chatbot/Model Agnostic: Let any LLM or chatbot client or agent you prefer automate your browser. Use Your Original Browser: Seamlessly integrate with your existing browser environment (your configurations, login states, etc.)

เซิร์ฟเวอร์ MCP MCP Chrome

Power your agent

เพิ่มเซิร์ฟเวอร์นี้

การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP

รันบน PlugMCP

Host a copy with our keys and logs.

ยังไม่มีรีลีสแบบแพ็กเกจในรีจิสทรี ทำตาม README ของรีโพซิทอรี.

รีโพซิทอรีการติดตั้งจากผู้เผยแพร่ทีละขั้นตอน: เพิ่มใน Claude

URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร

รันบน PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

เปิด

ข้อมูลเซิร์ฟเวอร์

โลคัล

ทรานสปอร์ต: stdio
สัญญาอนุญาต: MIT
ตรวจสอบล่าสุด: 2026-11-08

จากผู้เผยแพร่

เอกสารประกอบ

Chrome MCP Server 🚀

🌟 Turn your Chrome browser into your intelligent assistant - Let AI take control of your browser, transforming it into a powerful AI-controlled automation tool.

📖 Documentation: English | 中文

The project is still in its early stages and is under intensive development. More features, stability improvements, and other enhancements will follow.

🎯 What is Chrome MCP Server?

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search. Unlike traditional browser automation tools (like Playwright), Chrome MCP Server directly uses your daily Chrome browser, leveraging existing user habits, configurations, and login states, allowing various large models or chatbots to take control of your browser and truly become your everyday assistant.

✨ New Features(2025/12/30)

A New Visual Editor for Claude Code & Codex, for more detail here: VisualEditor

✨ Core Features

😁 Chatbot/Model Agnostic: Let any LLM or chatbot client or agent you prefer automate your browser
⭐️ Use Your Original Browser: Seamlessly integrate with your existing browser environment (your configurations, login states, etc.)
💻 Fully Local: Pure local MCP server ensuring user privacy
🚄 Streamable HTTP: Streamable HTTP connection method
🏎 Cross-Tab: Cross-tab context
🧠 Semantic Search: Built-in vector database for intelligent browser tab content discovery
🔍 Smart Content Analysis: AI-powered text extraction and similarity matching
🌐 20+ Tools: Support for screenshots, network monitoring, interactive operations, bookmark management, browsing history, and 20+ other tools
🚀 SIMD-Accelerated AI: Custom WebAssembly SIMD optimization for 4-8x faster vector operations

🆚 Comparison with Similar Projects

Comparison Dimension	Playwright-based MCP Server	Chrome Extension-based MCP Server
Resource Usage	❌ Requires launching independent browser process, installing Playwright dependencies, downloading browser binaries, etc.	✅ No need to launch independent browser process, directly utilizes user's already open Chrome browser
User Session Reuse	❌ Requires re-login	✅ Automatically uses existing login state
Browser Environment	❌ Clean environment lacks user settings	✅ Fully preserves user environment
API Access	⚠️ Limited to Playwright API	✅ Full access to Chrome native APIs
Startup Speed	❌ Requires launching browser process	✅ Only needs to activate extension
Response Speed	50-200ms inter-process communication	✅ Faster

🚀 Quick Start

Prerequisites

Node.js >= 20.0.0 and pnpm/npm
Chrome/Chromium browser

Installation Steps

Download the latest Chrome extension from GitHub

Download link: https://github.com/hangwin/mcp-chrome/releases

Install mcp-chrome-bridge globally

npm

npm install -g mcp-chrome-bridge

pnpm

# Method 1: Enable scripts globally (recommended)
pnpm config set enable-pre-post-scripts true
pnpm install -g mcp-chrome-bridge

# Method 2: Manual registration (if postinstall doesn't run)
pnpm install -g mcp-chrome-bridge
mcp-chrome-bridge register

Note: pnpm v7+ disables postinstall scripts by default for security. The enable-pre-post-scripts setting controls whether pre/post install scripts run. If automatic registration fails, use the manual registration command above.

Load Chrome Extension
- Open Chrome and go to chrome://extensions/
- Enable "Developer mode"
- Click "Load unpacked" and select your/dowloaded/extension/folder
- Click the extension icon to open the plugin, then click connect to see the MCP configuration

Usage with MCP Protocol Clients

Using Streamable HTTP Connection (👍🏻 Recommended)

Add the following configuration to your MCP client configuration (using CherryStudio as an example):

Streamable HTTP connection method is recommended

{
  "mcpServers": {
    "chrome-mcp-server": {
      "type": "streamableHttp",
      "url": "http://127.0.0.1:12306/mcp"
    }
  }
}

Using STDIO Connection (Alternative)

If your client only supports stdio connection method, please use the following approach:

First, check the installation location of the npm package you just installed

# npm check method
npm list -g mcp-chrome-bridge
# pnpm check method
pnpm list -g mcp-chrome-bridge

Assuming the command above outputs the path: /Users/xxx/Library/pnpm/global/5 Then your final path would be: /Users/xxx/Library/pnpm/global/5/node_modules/mcp-chrome-bridge/dist/mcp/mcp-server-stdio.js

Replace the configuration below with the final path you just obtained

{
  "mcpServers": {
    "chrome-mcp-stdio": {
      "command": "npx",
      "args": [
        "node",
        "/Users/xxx/Library/pnpm/global/5/node_modules/mcp-chrome-bridge/dist/mcp/mcp-server-stdio.js"
      ]
    }
  }
}

eg：config in augment:

🛠️ Available Tools

Complete tool list: Complete Tool List

get_windows_and_tabs - List all browser windows and tabs
chrome_navigate - Navigate to URLs and control viewport
chrome_switch_tab - Switch the current active tab
chrome_close_tabs - Close specific tabs or windows
chrome_go_back_or_forward - Browser navigation control
chrome_inject_script - Inject content scripts into web pages
chrome_send_command_to_inject_script - Send commands to injected content scripts

chrome_screenshot - Advanced screenshot capture with element targeting, full-page support, and custom dimensions

chrome_network_capture_start/stop - webRequest API network capture
chrome_network_debugger_start/stop - Debugger API with response bodies
chrome_network_request - Send custom HTTP requests

search_tabs_content - AI-powered semantic search across browser tabs
chrome_get_web_content - Extract HTML/text content from pages
chrome_get_interactive_elements - Find clickable elements
chrome_console - Capture and retrieve console output from browser tabs

chrome_click_element - Click elements using CSS selectors
chrome_fill_or_select - Fill forms and select options
chrome_keyboard - Simulate keyboard input and shortcuts

chrome_history - Search browser history with time filters
chrome_bookmark_search - Find bookmarks by keywords
chrome_bookmark_add - Add new bookmarks with folder support
chrome_bookmark_delete - Delete bookmarks

🧪 Usage Examples

AI helps you summarize webpage content and automatically control Excalidraw for drawing

prompt: excalidraw-prompt Instruction: Help me summarize the current page content, then draw a diagram to aid my understanding. https://www.youtube.com/watch?v=3fBPdUBWVz0

https://github.com/user-attachments/assets/fd17209b-303d-48db-9e5e-3717141df183

After analyzing the content of the image, the LLM automatically controls Excalidraw to replicate the image

prompt: excalidraw-prompt|content-analize Instruction: First, analyze the content of the image, and then replicate the image by combining the analysis with the content of the image. https://www.youtube.com/watch?v=tEPdHZBzbZk

https://github.com/user-attachments/assets/60d12b1a-9b74-40f4-994c-95e8fa1fc8d3