Read data from a page
retrieve_dataReads data from a single web page without altering it, returning structured output when a result schema is supplied. Use it when no clicking, typing or multi-page navigation is needed.
Instructions
Open one page and read data from it without changing anything on it. Returns the data, shaped by result_schema when given. Use run_task instead when getting to the data takes clicking, typing or several pages. If reading is still going when the call returns, the reply has status "running" and a task_id: call get_task with it.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>",
"prompt": "<prompt>"
},
"name": "retrieve_data"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The page to read (http or https). | |
| effort | No | How much capability to spend. Default medium; raise it for hard pages, lower it for simple ones. | |
| prompt | Yes | What to read from the page, e.g. "every listing with its title, price and link". | |
| use_proxy | No | Route the browser through the proxy configured in this server's environment. Default false. | |
| show_browser | No | Show the browser window while the task runs. Default false unless the server was started with --headed. | |
| result_schema | No | JSON Schema describing the shape of the data to return, for example {"type":"object","properties":{"price":{"type":"number"}},"required":["price"]}. Omit it for a free-form answer. |