
Chrome Devtools Cli
This is a CLI wrapper around Chrome DevTools Protocol that lets you automate browsers from the command line or scripts. You take snapshots to get element UIDs, then click, fill, or drag them around. State persists across commands, so you can chain actions without ceremony. It handles the stuff you'd expect like navigation, screenshots, and network inspection, plus less common needs like Lighthouse audits, performance traces, and heap snapshots. The snapshot approach is smarter than raw DOM selectors since it uses the accessibility tree. If you're building browser automation that needs to be scriptable or want DevTools power outside the GUI, this does the job without fighting Selenium.
- skills.sh installs
- 8.3K
- GitHub stars
- 55K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add chromedevtools/chrome-devtools-mcp --skill chrome-devtools-cli --agent claude-codeInstalls into .claude/skills of the current project.
Files
The chrome-devtools-mcp CLI lets you interact with the browser from your terminal.
Setup
Note: If this is your very first time using the CLI, see references/installation.md for setup. Installation is a one-time prerequisite and is not part of the regular AI workflow.
AI Workflow
- Execute: Run tools directly. If you don't know the target page's ID, run
chrome-devtools list_pagesto find it. The background server starts implicitly; do not runstart/status/stopbefore each use. - Inspect: Use
chrome-devtools take_snapshot <pageId>to get an element<uid>. - Act: Use
chrome-devtools click <pageId> <uid>,chrome-devtools fill <pageId> <uid> <value>, etc. State persists across commands.
Snapshot example:
uid=1_0 RootWebArea "Example Domain" url="https://example.com/"
uid=1_1 heading "Example Domain" level="1"
Permissions & File Access
Sponsors
Details
- Repository
- github.com/chromedevtools/chrome-devtools-mcp
- Categories
- AI & Agent Building, Automation & Workflows, CLI & Terminal
- First seen
- May 16, 2026