- Home
- MCP servers
- Chrome Debug
Chrome Debug
- javascript
8
GitHub Stars
javascript
Language
6 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": {
"rainmen-xia-chrome-debug-mcp": {
"command": "npx",
"args": [
"chrome-debug-mcp"
]
}
}
}This MCP Server lets you automate Chrome by connecting to an existing Chrome debug port, enabling browser actions while preserving login sessions. It is designed for zero-dependency deployment, container-friendly setups, and secure, local operation without relying on extensions.
How to use
You use an MCP client to drive Chrome through the MCP Server. Start a Chrome instance with debugging enabled, then run the MCP Server so it can connect to that port and manage browser actions. You can perform navigation, interaction, typing, scrolling, and content retrieval, all while reusing an existing logged-in session.
How to install
Prerequisites: install Node.js and npm on your system.
# 1) Start Chrome in debug mode (macOS example)
/Applications/Google\\ Chrome.app/Contents/MacOS/Google\\ Chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-debug
# 2) Run MCP server directly (recommended)
npx chrome-debug-mcp
Configuration & usage examples
Configure your MCP client to connect to the MCP Server. Choose a local stdio setup (the server runs as a local process) or a global install that you invoke from the client. Use these example configurations as a starting point.
{
"mcpServers": {
"browser-automation": {
"command": "npx",
"args": ["chrome-debug-mcp"]
}
}
}
Alternative installation methods
If you prefer a global installation, install the MCP server globally and reference it directly from your client.
{
"mcpServers": {
"browser-automation": {
"command": "chrome-debug-mcp"
}
}
}
Available tools
launch_browser
Connect to the running Chrome debugging port and establish a browser session for automation.
navigate_to
Navigate the current browser tab to a specified URL with intelligent tab reuse.
click
Click at specified coordinates or within the active element to simulate user interaction.
type_text
Type the provided text into the focused input field or element.
scroll_down
Scroll the page downward to reveal content not in view.
scroll_up
Scroll the page upward to revisit content above.
hover
Move the mouse pointer to a specified coordinate to trigger hover interactions.
resize_browser
Resize the browser window to given dimensions.
get_page_content
Retrieve the HTML content of the current page for validation or scraping.
close_browser
Close the current browser session and clean up the connection.