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 [blocked] 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:
Permissions & File Access
By default, the CLI has full filesystem access (--allowUnrestrictedPaths=true), allowing file-saving parameters (--filePath, --outputDirPath) and upload_file to access files anywhere on the system. Pass --allowUnrestrictedPaths=false if you want to restrict file access to the OS temp directory.
Command Usage
- Required arguments are passed positionally; optional arguments use flags.
- Use
--helpon any command for usage details. - Output defaults to plain Markdown-like text; pass
--output-format=jsonfor JSON.
Input Automation (<uid> from snapshot)
Navigation
Emulation
Performance
Memory
Memory Debugging (requires --memoryDebugging=true)
Network
Debugging & Inspection
Extensions
Progressive Web Apps (requires --categoryPwa=true)
Experimental Features
Experimental tools are disabled by default. Enable them with the corresponding flag during start.


