- Home
- MCP servers
- Chrome DevTools
Chrome DevTools
- python
3
GitHub Stars
python
Language
4 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"xrealsys-chrome-devtool-mcp": {
"command": "python",
"args": [
"/path/to/chrome-devtool-mcp/mcp_server.py"
],
"env": {
"MCP_HOST": "127.0.0.1",
"MCP_PORT": "12524",
"CLAUDE_MCP_CHROME_DEVTOOLS": "python /path/to/chrome-devtool-mcp/mcp_server.py"
}
}
}
}You can run a Chrome DevTools MCP Server to remotely control and inspect Chrome or other V8-based browsers. It lets you start and manage a Chrome instance, connect to debugging sessions, inspect DOM, monitor network activity, execute JavaScript in page context, set breakpoints, take screenshots, and perform comprehensive debugging from an MCP client.
How to use
You use an MCP client to talk to the Chrome DevTools MCP Server. Start the server locally, then connect from your client either by providing the server’s URL or by launching a local process that the MCP client can communicate with.
How to install
Prerequisites: Python 3.7+ and Google Chrome. The server runs on your machine and exposes an MCP interface for your tools to connect to.
Install steps you can follow exactly.
Configuration and usage notes
You can integrate the server with clients via two common approaches shown below. Use the one that matches your workflow.
Troubleshooting and tips
If you encounter connection issues, verify the server is running, check the port, and ensure the client can reach the server. Look for error details in the server logs for guidance.
Examples and capabilities
The server exposes a rich set of tools to automate and inspect Chrome. Typical actions include launching Chrome, navigating to pages, retrieving the DOM, inspecting network traffic, evaluating JavaScript in the page context, setting breakpoints, and taking screenshots.
Available tools
launch_chrome
Start a Chrome browser instance, optionally in headless mode, to begin a debugging session.
connect_remote_chrome
Connect to a remote Chrome/Chromium instance or Electron app for debugging.
connect_websocket_url
Directly attach to a debug session via a WebSocket URL to switch targets.
list_available_targets
List all open targets such as pages or tabs available for debugging.
navigate_to
Navigate the active target to a specified URL.
get_dom_tree
Retrieve the DOM tree structure of the current page at a given depth.
query_elements
Query DOM elements using a CSS selector to select elements of interest.
get_network_logs
Capture and inspect network requests and responses in real time.
get_console_logs
Fetch console output including logs, warnings, and errors.
execute_javascript
Execute JavaScript code in the context of the current page.
take_screenshot
Capture a screenshot of the current page or the full page.
get_page_info
Obtain basic information about the current page, such as title and URL.
get_script_sources
List all loaded JavaScript sources with metadata.
get_script_source
Retrieve the source code of a specific script by its identifier.
search_in_scripts
Search functions, classes, or text across loaded scripts.
get_page_functions
List all functions defined on the page context.
set_breakpoint
Set JavaScript breakpoints of various types (dom, event, function, xhr, line, logpoint).
list_breakpoints
List all active breakpoints currently set.
remove_breakpoint
Remove a specific breakpoint by its identifier.
get_paused_info
Get details about the current pause state and call stack.
resume_execution
Resume execution after hitting a breakpoint.
step_over
Step over the current line of code.
close_chrome
Close the active Chrome instance.