chrome-agent-mcp
Enables AI agents to fully control Google Chrome: navigate, click, fill forms, inspect DevTools, and manage tabs with parallel execution and session isolation.
README
<div align="center">
chrome-agent-mcp
Full Chrome control for AI agents via the Model Context Protocol
Give Claude (or any MCP client) full control over your browser: navigate pages, click elements, fill forms, inspect DevTools — with parallel tab execution, session isolation per agent, and a real-time dashboard.
</div>
What it does
Each Claude session gets its own Chrome tab group — so multiple agents can run in parallel without stepping on each other. A companion Chrome extension shows a live dashboard: active tabs, event log, and screenshots in real time.
Claude session A → tab group "Pinguim" (blue)
Claude session B → tab group "Fenix" (red)
Claude session C → tab group "Girafa" (yellow)
Every tool call is wrapped with resilient execution:
- 20 s primary timeout
- 2× parallel retries on timeout (10 s each)
- Automatic fallback to a new Chrome group if all retries fail
Requirements
- Node.js ≥ 18
- Google Chrome with remote debugging enabled
Installation
1. Enable Chrome remote debugging
google-chrome --remote-debugging-port=9222
To make it permanent, add the flag to your Chrome launcher or .desktop file.
2. Install the MCP server
# Run directly (no install)
npx chrome-agent-mcp
# Or install globally
npm install -g chrome-agent-mcp
3. Configure your MCP client
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"chrome-agent-mcp": {
"command": "npx",
"args": ["chrome-agent-mcp"],
"env": { "CHROME_DEBUG_PORT": "9222" }
}
}
}
Claude Code (.claude/settings.json):
{
"mcpServers": {
"chrome-agent-mcp": {
"command": "node",
"args": ["/path/to/chrome-agent-mcp/dist/index.js"],
"env": { "CHROME_DEBUG_PORT": "9222" }
}
}
}
4. Install the companion extension (optional but recommended)
- Open
chrome://extensions/ - Enable Developer mode
- Click Load unpacked → select the
extension/folder
The extension adds a popup dashboard showing which tabs are active, what the agent is doing, and captured screenshots — all updating in real time.
Available Tools
Navigation
| Tool | Description |
|---|---|
browser_navigate |
Navigate to a URL |
browser_navigate_back |
Go back in browser history |
browser_navigate_forward |
Go forward in browser history |
browser_reload |
Reload the current tab |
Interaction
| Tool | Description |
|---|---|
browser_click |
Click an element by accessibility ref |
browser_type |
Type text into a focused element |
browser_hover |
Hover over an element |
browser_press_key |
Press a keyboard key or shortcut |
browser_scroll |
Scroll the page or an element |
browser_select_option |
Select a <select> dropdown option |
browser_fill_form |
Fill multiple form fields at once |
browser_wait_for |
Wait for an element or condition |
Page Inspection
| Tool | Description |
|---|---|
browser_snapshot |
Get the accessibility tree of the page |
browser_take_screenshot |
Capture a full-page screenshot |
browser_evaluate |
Execute JavaScript and return the result |
Tab Management
| Tool | Description |
|---|---|
browser_tabs |
Open, close, switch, list, and mark tabs done |
DevTools
| Tool | Description |
|---|---|
devtools_console |
Read and clear browser console logs |
devtools_network |
Inspect network requests and responses |
devtools_elements |
Inspect and query DOM elements |
devtools_storage |
Read cookies, localStorage, sessionStorage |
Browser Management
| Tool | Description |
|---|---|
chrome_windows |
List all open Chrome windows |
chrome_focus |
Focus a specific window |
chrome_extensions |
List installed Chrome extensions |
session_sync |
Sync session state with the extension dashboard |
Architecture
src/
├── index.ts MCP server + request dispatch
├── types.ts Shared type definitions
├── core/ Infrastructure layer
│ ├── connection.ts Chrome CDP connection lifecycle
│ ├── bridge.ts Extension event bridge
│ ├── favicon.ts Tab favicon animation manager
│ ├── resilience.ts Timeout / retry / fallback execution
│ └── groups/ Tab group isolation
│ ├── manager.ts Orchestrator (public API)
│ ├── state.ts File-based state persistence
│ └── chrome-api.ts Chrome Extension API bridge
├── tools/ MCP tool implementations
│ ├── tabs.ts
│ ├── navigation.ts
│ ├── browser.ts
│ ├── media.ts screenshot · snapshot · evaluate
│ ├── session.ts
│ ├── interaction/ click · type · hover · scroll · form · wait
│ └── devtools/ console · network · elements · storage
└── utils/ Pure utility functions
├── accessibility.ts AX tree formatter
├── description.ts Tab action labels
└── identity.ts Animal names + Chrome group colors
Engineering rules: every file ≤ 300 lines · every directory ≤ 7 items · SOLID principles throughout.
Configuration
| Variable | Default | Description |
|---|---|---|
CHROME_DEBUG_PORT |
9222 |
Chrome remote debugging port |
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Watch mode
npm run dev
# Run tests
npm test
# Coverage report (target: 80%)
npm run coverage
License
MIT © Otavio Senne
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。