browser_get_interactives
browser_get_interactivesLists interactive page elements and their opaque element_ids so an agent can inspect a page or iframe and target the right control before performing any element action.
Instructions
List interactive page elements and their opaque element_ids. Call this before any element action. Pass frame_id to inspect an iframe; the top document is frame 0, and an element_id only works in the frame that returned it. A heavy page can hold hundreds of elements, so the list is capped at 150 and reports total plus truncated; narrow it with limit, visible_only, tag, role or name_contains instead of asking for everything.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "browser_get_interactives"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | Keep one tag, for example button or input. | |
| role | No | Keep one role, for example tab or combobox. | |
| limit | No | Maximum elements returned. Defaults to 150. | |
| tab_id | No | Chrome tab ID. Defaults to the active tab when omitted. | |
| frame_id | No | Chrome frame ID inside the tab from browser_get_frames. 0 is the top document, which is the default. | |
| session_id | No | Session that owns the tab. Pass it on every call so the runtime can refuse a tab another session holds. | |
| session_name | No | Name for this conversation's Chrome tab group, so the tab bar reads as the task instead of a generated id. Sticky: pass it once when the name becomes clear, and again only to rename. | |
| visible_only | No | Drop elements that are not visible. | |
| name_contains | No | Case-insensitive substring of the element name or text. |