click
在指定坐标位置点击
LABSCO SUMMARY
Attaching to your logged-in browser is the whole trick; the tool set is deliberately small.
Actions are coordinate-based rather than selector-based, which pairs with the screenshot returned after each step — the model looks, then aims. That is coarser than an accessibility-tree approach, but it needs no extension and no store approval, which is why it still works in a locked-down environment or a container where those are not options.
What it is
A browser-automation server that connects to a Chrome instance started in debugging mode. Because it attaches to your existing browser rather than launching a clean one, the sessions you are already logged into stay logged in.
What you get
- launch_browser to attach to the debugging port and open a session, close_browser to release it
- navigate_to with tab reuse — the same domain reuses its tab instead of piling up new ones
- click and hover by coordinates, type_text for input, scroll_down and scroll_up a viewport at a time
- resize_browser to change the window size, and get_page_content for the current page's HTML
- A screenshot after each operation for visual feedback, and an automatic wait for network activity to settle
Requirements
Node, and a Chrome started in debugging mode with its own user data directory. It works the same against a Chrome running in a container, which the server discovers on its own.
Setup effort
One command — npx chrome-debug-mcp
USE CASES
01
Automating a site that requires login
Sign in yourself once in the debug-mode browser, then let the agent work inside that same session.
02
Filling a form on a page you can see
Look at the screenshot, aim at the field, type, and submit.
03
Reading a page that only renders when signed in
Navigate and pull the page's HTML with your session intact.
04
Getting to content further down the page
Scroll a viewport at a time and re-read the page after each step.
05
Running the same flow inside a container
Point at a containerised Chrome instead of a local one; discovery is automatic.
10 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
close_browser
关闭浏览器连接
get_page_content
获取当前页面的HTML内容
hover
将鼠标悬停在指定坐标位置
launch_browser
启动浏览器连接，连接到Chrome调试端口以保持登录状态
navigate_to
导航到指定URL，智能管理标签页（相同域名复用标签页）
resize_browser
调整浏览器窗口大小
scroll_down
向下滚动页面一个视口高度
scroll_up
向上滚动页面一个视口高度
type_text
输入文本内容
BEFORE YOU INSTALL
What to know first
Tools you get
10 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 10 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"chrome-debug-mcp": {
"command": "npx",
"args": [
"chrome-debug-mcp"
]
}
}
}npx
TERMINAL
npx chrome-debug-mcp
