Start a GENERIC human-in-the-loop co-browse: opens a headful browser with a persistent profile, navigates to a URL, and returns frame/input HTTP paths so a human can solve a captcha or log in remotely. Automation resumes on the SAME session (cookies/auth persist on disk) afterward. The remote UI ...
AI agents invoke browser_interactive_start to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | URL to open for the human to interact with |
width | integer | — | Viewport width (default: 1280) |
height | integer | — | Viewport height (default: 800) |
prefill | array | — | Optional fields to prefill before handing control to the human |
profile | string | — | Persistent user-data-dir (default: ~/.yaver/browser-profiles/<session_id>) |
session_id | string | — | Custom session ID (auto-generated if omitted) |
Parameters from the server's own tool schema.
browser_interactive_start triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
Start a GENERIC human-in-the-loop co-browse: opens a headful browser with a persistent profile, navigates to a URL, and returns frame/input HTTP paths so a human can solve a captcha or log in remotely. Automation resumes on the SAME session (cookies/auth persist on disk) afterward. The remote UI polls frame_path for JPEG frames and POSTs {type:click|key|scroll,...} to input_path. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
browser_interactive_start accepts 6 parameters: url, width, height, prefill, profile, session_id. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for browser_interactive_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.
browser_interactive_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the browser_interactive_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser_interactive_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser_interactive_start is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.