Start a browser-agent task (billed)
browseAutomate browser interactions like filling forms, using a site's search, or reaching pages behind clicks; submit a task to a hosted agent and poll the returned handle for results.
Instructions
Hand a task to a hosted browser agent that clicks and types until done: MINUTES, billed per task. For forms, a site's own search, pages behind interaction; a URL you have is extract's. After 25s it returns a handle: poll browse_status, since calling this again pays for a second task. NOTHING IS CONFIGURED FOR THIS METHOD on this machine, so every call will fail. A key in one of BROWSERBASE_API_KEY, BROWSER_USE_API_KEY, SKYVERN_API_KEY turns it on: see load_env.
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": {
"task": "<task>"
},
"name": "browse"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | What the agent should do in the browser, in plain words. | |
| provider | No | ||
| max_steps | No | Upper bound on the actions the agent may take. | |
| start_url | No | The page the agent starts on. Some backends cannot start without one, and say so. | |
| output_schema | No | JSON Schema the answer must conform to. Omit it to get prose instead. | |
| allowed_domains | No | Keep the agent on these domains. |