| name | chrome-mcp |
| description | Observable browser automation using Chrome MCP tools. Use when you need to browse websites, take screenshots, interact with web pages, or perform browser tasks in your current Chrome. Keywords - browse, screenshot, browser, chrome, ui testing, observable. |
Chrome MCP
Purpose
Automate browsing using Chrome MCP tools (mcp__claude_in_chrome__*) available when Claude Code is started with --chrome. This uses your real Chrome browser — observable, with your existing profile, cookies, and extensions.
Pre-flight Check
Before doing anything, verify Chrome MCP tools are available. Look for tools matching mcp__claude_in_chrome__*.
- If available: proceed with the workflow.
- If NOT available: stop and reply to the user: "Chrome tools are not available. Please restart Claude Code with the
--chrome flag: claude --chrome"
Workflow
- Resize the browser window to 1440x900
- Execute the user's request using Chrome MCP tools (navigate, click, screenshot, etc.)
- Report results back to the user
Limitations
- No parallel instances. All Chrome MCP connections share a single Chrome extension controller. Only one task at a time.
- Observable only. This uses your real Chrome — there is no headless mode.
