Chrome DevTools MCP
About
Official Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.
Explore
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Chrome DevTools MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"chrome devtools mcp": {
"server": {
"command": "npx",
"args": [
"-y",
"chrome-devtools-mcp"
]
}
}
}
}
McpServers
{
"server": {
"command": "npx",
"args": [
"-y",
"chrome-devtools-mcp"
]
}
}
Transport
"stdio"
Package
"chrome-devtools-mcp"
Registry
"npm"
What can you do with Chrome DevTools MCP?
- Performance tracing— Ask your assistant to record a trace withperformance_start_traceand analyze insights like Core Web Vitals for any page.
- Network debugging— Uselist_network_requestsandget_network_requestto inspect failed requests, status codes, and response details.
- Console monitoring— Checklist_console_messagesfor errors and warnings with source-mapped stack traces to debug issues.
- Page automation— Direct your assistant tonavigate_page,click,fill_form, ortake_screenshotto interact with and capture live pages.
- Memory analysis— Enable memory debugging to take and compare heap snapshots, query objects, and trace retaining paths for leaks.
- Lighthouse audits— Runlighthouse_auditto get performance, accessibility, and SEO scores for a URL.
Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live Chrome browser. It acts as a Model-Context-Protocol (MCP) server, giving your AI coding assistant access to the full power of Chrome DevTools for reliable automation, in-depth debugging, and performance analysis. A[CLIis also provided for use without MCP.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



