| name | agent-browser-query |
| version | 1.0.0 |
| description | Query page content: get text, HTML, attributes, element state, accessibility
snapshots, and find elements by role, text, label, placeholder, or testid.
|
| allowed-tools | ["Bash","Read"] |
Agent Browser: Query & Find
Extract information from pages and locate elements.
Get Element Content
agent-browser get text <sel>
agent-browser get html <sel>
agent-browser get value <sel>
agent-browser get attr <sel> <attr>
Get Page Info
agent-browser get title
agent-browser get url
agent-browser get count <sel>
agent-browser get box <sel>
agent-browser get styles <sel>
Element State Checks
agent-browser is visible <sel>
agent-browser is enabled <sel>
agent-browser is checked <sel>
Accessibility Snapshot
agent-browser snapshot
agent-browser snapshot -i
agent-browser snapshot -C
agent-browser snapshot -c
agent-browser snapshot -d
agent-browser snapshot -s
Find Elements by Semantic Locators
All find commands take an <action> (click, fill, type, etc.) and optional [value].
agent-browser find role <role> <action> [value]
agent-browser find text <text> <action>
agent-browser find label <label> <action> [value]
agent-browser find placeholder <ph> <action> [value]
agent-browser find alt <text> <action>
agent-browser find title <text> <action>
agent-browser find testid <id> <action> [value]
Positional Find
agent-browser find first <sel> <action> [value]
agent-browser find last <sel> <action> [value]
agent-browser find nth <n> <sel> <action> [value]
Examples
agent-browser get title
agent-browser is visible "button.login"
agent-browser find role button click --name "Submit"
agent-browser find label "Email" fill "user@example.com"
agent-browser snapshot -C
Guidelines
- Use
snapshot to understand page structure before interacting
- Prefer semantic locators (
find role, find label) over CSS selectors
--exact flag enables exact text matching (default is substring)
- State checks return exit code 0 (true) or 1 (false) for scripting