Chrome Tools MCP Server
An MCP server that provides tools for interacting with Chrome through its DevTools Protocol. This server enables remote control of Chrome tabs, including executing JavaScript, capturing screenshots, monitoring network traffic, and more.
Why use an MCP server like this?
This type of MCP Server is useful When you need to manually configure your browser to be in a certain state before you let an AI tool like Cline poke at it. You can also use this tool to listen to and pull network events into its context.
Features
- List Chrome tabs
- Execute JavaScript in tabs
- Capture screenshots
- Monitor network traffic
- Navigate tabs to URLs
- Query DOM elements
- Click elements with console output capture
Installation
Configuration
The server can be configured through environment variables in your MCP settings:
Environment Variables
CHROME_DEBUG_URL: The URL where Chrome's remote debugging interface is available (default: http://localhost:9222)
CHROME_CONNECTION_TYPE: Connection type identifier for logging (e.g., "direct", "ssh-tunnel", "docker")
CHROME_ERROR_HELP: Custom error message shown when connection fails
Setup Guide
Native Setup (Windows/Mac/Linux)
- Launch Chrome with remote debugging enabled:
- Configure MCP settings:
WSL Setup
When running in WSL, you'll need to set up an SSH tunnel to connect to Chrome running on Windows:
- Launch Chrome on Windows with remote debugging enabled
- Create an SSH tunnel:
- Configure MCP settings:
Docker Setup
When running Chrome in Docker:
- Launch Chrome container:
- Configure MCP settings:
Tools
list_tabs
Lists all available Chrome tabs.
execute_script
Executes JavaScript code in a specified tab.
Parameters:
tabId: ID of the Chrome tab
script: JavaScript code to execute
capture_screenshot
Captures a screenshot of a specified tab, automatically optimizing it for AI model consumption.
Parameters:
tabId: ID of the Chrome tab
format: Image format (jpeg/png) - Note: This is only for initial capture. Final output uses WebP with PNG fallback
quality: JPEG quality (1-100) - Note: For initial capture only
fullPage: Capture full scrollable page
Image Processing:
- WebP Optimization (Primary Format):
- PNG Fallback:
- Size Constraints:
capture_network_events
Monitors and captures network events from a specified tab.
Parameters:
tabId: ID of the Chrome tab
duration: Duration in seconds to capture
filters: Optional type and URL pattern filters
load_url
Navigates a tab to a specified URL.
Parameters:
tabId: ID of the Chrome tab
url: URL to load
query_dom_elements
Queries and retrieves detailed information about DOM elements matching a CSS selector.
Parameters:
tabId: ID of the Chrome tab
selector: CSS selector to find elements Returns:
- Array of DOM elements with properties including:
click_element
Clicks on a DOM element and captures any console output triggered by the click.
Parameters:
tabId: ID of the Chrome tab
selector: CSS selector to find the element to click Returns:
- Object containing:
License
MIT
Chrome Tools MCP Server
An MCP server that provides tools for interacting with Chrome through its DevTools Protocol. This server enables remote control of Chrome tabs, including executing JavaScript, capturing screenshots, monitoring network traffic, and more.
Why use an MCP server like this?
This type of MCP Server is useful When you need to manually configure your browser to be in a certain state before you let an AI tool like Cline poke at it. You can also use this tool to listen to and pull network events into its context.
Features
- List Chrome tabs
- Execute JavaScript in tabs
- Capture screenshots
- Monitor network traffic
- Navigate tabs to URLs
- Query DOM elements
- Click elements with console output capture
Installation
Configuration
The server can be configured through environment variables in your MCP settings:
Environment Variables
CHROME_DEBUG_URL: The URL where Chrome's remote debugging interface is available (default: http://localhost:9222)
CHROME_CONNECTION_TYPE: Connection type identifier for logging (e.g., "direct", "ssh-tunnel", "docker")
CHROME_ERROR_HELP: Custom error message shown when connection fails
Setup Guide
Native Setup (Windows/Mac/Linux)
- Launch Chrome with remote debugging enabled:
- Configure MCP settings:
WSL Setup
When running in WSL, you'll need to set up an SSH tunnel to connect to Chrome running on Windows:
- Launch Chrome on Windows with remote debugging enabled
- Create an SSH tunnel:
- Configure MCP settings:
Docker Setup
When running Chrome in Docker:
- Launch Chrome container:
- Configure MCP settings:
Tools
list_tabs
Lists all available Chrome tabs.
execute_script
Executes JavaScript code in a specified tab.
Parameters:
tabId: ID of the Chrome tab
script: JavaScript code to execute
capture_screenshot
Captures a screenshot of a specified tab, automatically optimizing it for AI model consumption.
Parameters:
tabId: ID of the Chrome tab
format: Image format (jpeg/png) - Note: This is only for initial capture. Final output uses WebP with PNG fallback
quality: JPEG quality (1-100) - Note: For initial capture only
fullPage: Capture full scrollable page
Image Processing:
- WebP Optimization (Primary Format):
- PNG Fallback:
- Size Constraints:
capture_network_events
Monitors and captures network events from a specified tab.
Parameters:
tabId: ID of the Chrome tab
duration: Duration in seconds to capture
filters: Optional type and URL pattern filters
load_url
Navigates a tab to a specified URL.
Parameters:
tabId: ID of the Chrome tab
url: URL to load
query_dom_elements
Queries and retrieves detailed information about DOM elements matching a CSS selector.
Parameters:
tabId: ID of the Chrome tab
selector: CSS selector to find elements Returns:
- Array of DOM elements with properties including:
click_element
Clicks on a DOM element and captures any console output triggered by the click.
Parameters:
tabId: ID of the Chrome tab
selector: CSS selector to find the element to click Returns:
- Object containing:
License
MIT