mcp-cui-chrome
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_CHROME_PATH | No | Chrome 不在默认位置时,填 chrome.exe 的完整路径 | |
| MCP_CHROME_PROFILE | No | 换一个配置目录(Chrome 配置目录的路径) | |
| MCP_CHROME_CDP_PORT | No | 给后启动的会话留的本机调试端口。不设或设为 0 时由 Chrome 自己选 | |
| MCP_CHROME_HEADLESS | No | 设为 1 时不显示窗口。有窗口时更接近真人使用 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
这是用户本机上单独的一个 Chrome,窗口左下角有黄色 cui-chrome 标签,不是 IDE 里内置的浏览器。用户说打开 Chrome、打开网页、访问网站、登录、点击、输入、滚动、看页面或刷新时,用本服务的工具,不要改用其他浏览器工具。先 browser_navigate 或 browser_snapshot,再按快照里的编号操作。相同地址的标签已经开着就切换过去。本该有的内容不在快照里时,用 browser_reload 刷新一次再读。快照写了遮挡,或点击报告被挡住,先关掉那一层或按 Escape。这些工具只做通用的浏览器操作,不要当成某个网站的专用流程。
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateA | 用户要打开 Chrome 或访问网页时用这个,不要用 IDE 内置浏览器。打开一个 http(s) 地址。相同地址的标签已存在就切换过去,没有再新建,不改别的标签。 |
| browser_snapshotA | 用户要看当前 Chrome 页面时用这个。读取标题、网址、可操作元素编号和正文。若本该有的内容不在,用 browser_reload 刷新一次再读。快照若写了遮挡,先关掉那一层或按 Escape。 |
| browser_clickA | 通用:按快照编号点击。开始前显示要点的元素,结束后显示是否成功、页面有没有跳转。落点被别的内容挡住时会失败,不点穿过去。 |
| browser_typeA | 通用:只对文本框逐字输入。下拉框、选项、按钮会直接失败,并说明该用点选还是点击。 |
| browser_pressB | 通用:在当前焦点按一个键。开始前显示键名,结束后显示是否成功。 |
| browser_hoverA | 通用:把鼠标移到编号对应的元素上,不点击。用来展开需要悬停才出现的菜单。 |
| browser_dragA | 通用:按住一个元素,拖到另一个元素上,或按像素偏移拖动。用于滑块、排序和需要拖动的控件。 |
| browser_scrollB | 通用:在当前页面分段滚动。开始前显示方向,结束后显示是否成功。 |
| browser_tabsC | 通用:列出、新建、切换或关闭标签。开始前说明要做什么,结束后说明是否成功。 |
| browser_reloadA | 通用:刷新当前标签,相当于 F5。快照里本该出现的按钮或正文没有时用一次,然后再读页面。不要连续反复刷新。 |
| browser_go_backA | 通用:当前标签后退一页。开始前说明,结束后显示是否退回到上一页。 |
| browser_screenshotA | 通用:截取当前视口。开始前在页面上说明,结束后返回图片并标明成功或失败。 |
| browser_closeA | 通用:关掉这次会话自己打开的 Chrome。如果窗口是别的会话打开的,只断开连接,窗口留着。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Each tool maps to a clearly distinct browser action (navigate, click, type, press, hover, drag, scroll, screenshot), and descriptions explicitly cross-reference siblings (e.g. snapshot vs reload, tabs vs navigate). Minor overlap remains between browser_navigate and browser_tabs for opening tabs, and between browser_snapshot and browser_screenshot, but the descriptions differentiate them well enough.
All 13 tools use the same browser_ prefix with snake_case, and the suffix is either a verb (navigate, click, type, press, hover, drag, scroll, reload) or a clearly paired noun (tabs, snapshot, screenshot, close). The pattern is predictable and readable throughout.
13 tools is well within the ideal 3–15 range and every tool corresponds to a real, non-redundant browser control primitive. Nothing feels padded or missing at the count level.
The surface covers the full browsing lifecycle: navigation, history, tabs, DOM reading, all common input/pointer interactions, screenshots, and session cleanup. Gaps exist for file upload, JS evaluation/console or network inspection, and explicit wait-for-condition, but core agent workflows are workable.