agent-browser-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BROWSER_MCP_DIALOGS | No | Dialog auto-handling policy: accept or dismiss (default accept). Equivalent to --dialogs accept|dismiss. | |
| BROWSER_MCP_PROFILE | No | Browser profile directory. Equivalent to --profile <dir>. | |
| BROWSER_MCP_CHANNELS | No | Browser channels to use, e.g. chrome,msedge. Equivalent to --channels chrome,msedge. | |
| BROWSER_MCP_HEADLESS | No | Run the browser in headless mode. Equivalent to the --headless command line argument. | |
| BROWSER_MCP_VIEWPORT | No | Viewport size, e.g. 1440x900. Equivalent to --viewport 1440x900. | |
| BROWSER_MCP_START_URL | No | Initial URL to open. Equivalent to --start-url <url>. | |
| BROWSER_MCP_EXECUTABLE | No | Path to the browser executable. Equivalent to --executable <path>. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateB | 导航到 URL,返回后自动附带页面交互元素快照(带 [eN] ref 编号,可直接用于 click/type)。缺协议时自动补 https://。 |
| browser_snapshotB | 获取当前页面语义快照:交互元素带 [eN] ref 编号(iframe 内容已拍平)。支持 rootRef(只看某元素子树)、selector、filter:"interactive" 只看交互元素。 |
| browser_clickA | 点击元素(优先用快照里的 ref)。自动等待可操作、自动重解析失效 ref、点击后自动附最新快照。特殊对话框会自动处理并上报。 |
| browser_typeB | 向输入框输入文本(先清空再输入)。submit:true 时回车提交。适用于 input/textarea/contenteditable。 |
| browser_press_keyC | 按下键盘按键,如 Enter / Tab / ArrowDown / "Control+a"。带 ref 时先聚焦该元素。 |
| browser_select_optionB | 在下拉框(select)中选中选项。values 可为 value 或可见 label,自动两轮匹配。 |
| browser_hoverC | 鼠标悬停到元素上(触发悬浮菜单/tooltip)。 |
| browser_scrollB | 滚动页面或指定滚动容器(带 ref 时滚动该容器)。方向 + 像素量。 |
| browser_screenshotA | 截屏并保存到本地,返回图片(供多模态查看)。可整页、可视区或单元素(ref)。 |
| browser_evaluateA | 逃生舱:在页面里执行 JS 并返回 JSON 可序列化结果。传函数字符串如 |
| browser_waitA | 等待条件成立:timeMs 固定时长 / text 文本出现 / selector 元素出现 / url 跳转 / idle 网络空闲。可组合。 |
| browser_tabsB | 多标签管理:list 列出 / new 新建 / select 切换(按 list 显示的 index 或 id)/ close 关闭。 |
| browser_get_infoA | 查询浏览器健康状态:模式、标签列表、重启次数、最近错误/对话框/下载。不会启动浏览器。 |
| browser_closeA | 关闭浏览器(launch 模式下整个浏览器退出,profile 登录态保留;connect 模式只断开连接)。下次工具调用会自动重启。 |
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 14 tools
Every tool targets a distinct action: navigate loads URLs, snapshot reads structure, wait blocks on conditions, and click/type/press_key/select_option/hover/scroll each map to a unique interaction primitive. The only mild overlap (navigate also returns a snapshot) is resolved by navigate requiring a URL, so an agent can always pick correctly. browser_evaluate is clearly labeled as an escape hatch rather than a duplicate of any other tool.
All 14 tools share a consistent `browser_` prefix and snake_case, with most following a verb or verb_noun form (navigate, click, press_key, select_option, get_info). Minor deviations exist: `browser_tabs` is a noun with a mode argument, and several actions are bare verbs without an object, but the set remains highly predictable.
14 tools is well-scoped for a browser automation server: one tool per core primitive (navigate, snapshot, wait, interact, screenshot, evaluate) plus tabs and lifecycle management. Nothing feels padded, and no obvious primitive is split into multiple redundant tools.
The surface covers the full browse-inspect-interact loop plus lifecycle, tabs, JS evaluation, and health diagnostics, which handles nearly all agent workflows. Gaps remain for history navigation (back/forward), file upload/download interaction, and drag-and-drop, though evaluate provides a viable workaround.