browser_operator
Drive a real browser on THIS machine toward a plain-language goal, one grounded action at a time (navigate / click / type / scroll / wait), and return a step trace. engine defaults to chrome; firefox and safari use real W3C WebDriver. Use this for multi-step web tasks; use browser_open + browser_...
This record as markdown: /tools/io-github-kivanccakmak-yaver/browser-operator.md
What browser_operator does on Yaver
AI agents invoke browser_operator 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 |
|---|---|---|---|
goal | string | Yes | What to accomplish, in plain language. |
engine | string | — | |
headful | boolean | — | Show the browser window (default headless; Safari is always headful). |
profile | string | — | Persistent profile name so cookies/clearance persist. |
maxSteps | integer | — | Action cap (default 10). |
startUrl | string | — | Optional URL to open first. |
sessionId | string | — | Reuse an open browser session; omit to open one. |
timeoutSec | integer | — | Total wall-clock budget (default 300). |
Parameters from the server's own tool schema.
Why browser_operator is rated High
Controls a real browser to perform arbitrary multi-step web actions on the machine.
From the tool's definition Drive a real browser... navigate / click / type / scroll / wait
Attacks that exploit this kind of access
The rule that runs browser_operator safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_operator, this is the rule to start with:
browser_operator stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every browser_operator call is checked against it from then on.
Questions about browser_operator
Drive a real browser on THIS machine toward a plain-language goal, one grounded action at a time (navigate / click / type / scroll / wait), and return a step trace. engine defaults to chrome; firefox and safari use real W3C WebDriver. Use this for multi-step web tasks; use browser_open + browser_click for a single known step. 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_operator accepts 8 parameters: goal, engine, headful, profile, maxSteps, startUrl, sessionId, timeoutSec. Required: goal. 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_operator: 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_operator 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_operator 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_operator. 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_operator 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.
More on Yaver, and thousands of servers like it.
Across the catalogue