What are the prerequisites for MCP Chrome Server?
Python 3.12, Google Chrome installed, and either `uv` (Python package installer) or Docker.
@dlwjdtn535
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-chrome-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@dlwjdtn535/mcp-chrome-server",
"--client",
"claude"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
MCP Chrome Server is a browser automation tool built on the MCP (Model-Controller-Prompt) framework. It integrates with Google Chrome to enable programmatic control of the browser, intended for developers and automation engineers.
Install via Smithery (npx -y @smithery/cli install @dlwjdtn535/mcp-chrome-server --client claude) or configure manually with uv and a JSON configuration for your OS. Set the CHROME_PROFILE_PATH environment variable to your Chrome profile directory, close all running Chrome instances, then use the provided tools (e.g., tool_open_browser, tool_navigate, tool_web_login).
Python 3.12, Google Chrome installed, and either `uv` (Python package installer) or Docker.
Set the `CHROME_PROFILE_PATH` environment variable to your Chrome profile directory. Defaults: Windows `%LOCALAPPDATA%\Google\Chrome\User Data`, macOS `~/Library/Application Support/Google/Chrome`, Linux `~/.config/google-chrome`.
Yes. It waits for the user to solve CAPTCHA when detected and automatically handles 2‑factor authentication during web login.
Credentials should be stored and retrieved using the system keychain via the `tool_save_credentials` and `tool_get_credentials` tools. Never expose credentials in environment variables or configuration files.
Close all other Chrome windows using the same profile, verify the profile path is correct, and ensure you have proper permissions for the Chrome profile directory.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
评论