browser-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEBAI_HOST | No | Host used for the Chrome debug port. | 127.0.0.1 |
| WEBAI_PORT | No | Chrome debug port. | 9222 |
| WEBAI_DEBUG | No | Set to 1 to include tracebacks in tool errors. | |
| WEBAI_NO_EVAL | No | Set to 1 to disable the web_eval tool. | |
| WEBAI_ALLOW_EVAL | No | Set to 0 to disable the web_eval tool. | |
| WEBAI_DOWNLOAD_DIR | No | Default directory for PDFs saved by web_download_pdf. | ~/Downloads |
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 |
|---|---|
| web_tabsA | List the open browser tabs (id, title, url). |
| web_new_tabB | Open a new tab, optionally at a URL. Returns its id. |
| web_close_tabC | Close a tab by id. |
| web_navigateC | Navigate a tab to a URL. |
| web_readB | Read the visible text of the page (document.body.innerText), with title and URL. |
| web_htmlC | Get outerHTML of the page, or of the element matching 'selector'. |
| web_clickA | Click an element by CSS 'selector', or the first clickable element whose visible text contains 'text'. |
| web_typeB | Type 'text' into the input/textarea matching 'selector'. Set submit=true to submit the form. |
| web_waitA | Wait until an element matching 'selector' appears (polls), up to timeout_seconds. |
| web_evalB | Run arbitrary JavaScript in the page and return the result. The power tool; can be disabled with WEBAI_NO_EVAL. |
| web_screenshotC | Capture a PNG screenshot of the tab. |
| web_download_pdfA | Save the current page as a PDF and return the file path. Optional 'path' (a file or a folder); defaults to ~/Downloads named after the page title. |
| web_switch_tabC | Bring a tab to the front / make it active, by id. |
| web_backA | Go back one entry in the tab's history (like the browser's Back button). |
| web_forwardB | Go forward one entry in the tab's history (like the browser's Forward button). |
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 15 tools
Each tool maps to a distinct browser action: tab lifecycle (list/new/close/switch), history (back/forward), navigation, inspection (read/html/eval/screenshot/pdf), and interaction (click/type/wait). The only mild overlap is web_eval versus web_read/web_html, but eval's arbitrary-JS purpose is clearly differentiated. An agent can reliably pick the right tool for a given intent.
All tools share a consistent 'web_' snake_case prefix, which makes the set instantly recognizable. Minor deviation: some names are verbs (web_click, web_navigate) while others are nouns (web_tabs, web_screenshot, web_html), but the convention remains readable and predictable.
Fifteen tools is well within the sweet spot and each one earns its place by covering a real browser primitive. There is no redundancy or filler in the surface.
Core lifecycle is fully covered: tab management, navigation, history, content extraction, interaction, waiting, and export (screenshot/PDF). Notable gaps remain for common automation needs — hover, select-option for dropdowns, keyboard key presses, scrolling, and iframe/frame targeting — which agents may have to work around via web_eval.