selenium_start
Start a first-class W3C WebDriver session on this runtime host. Supports Chrome, Firefox, and real Safari (macOS with safaridriver enabled). Does not bypass CAPTCHA or site auth; hand off to the user when needed.
This record as markdown: /tools/io-github-kivanccakmak-yaver/selenium-start.md
What selenium_start does on Yaver
AI agents invoke selenium_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 | — | Optional initial URL |
width | integer | — | Viewport width, default 1280 |
height | integer | — | Viewport height, default 800 |
record | boolean | — | Record the actual WebDriver session to an MP4 served through the task/video clip route. |
browser | string | — | Actual browser to launch. Defaults to chrome; Safari is real Safari, not Playwright WebKit. |
headful | boolean | — | Show Chrome window visibly |
profile | string | — | Persistent Chrome profile name or absolute user-data-dir |
session_id | string | — | Optional custom session ID |
record_seconds | integer | — | Recording safety cap; default 600 seconds. |
Parameters from the server's own tool schema.
Why selenium_start is rated High
Initiates browser automation with full control over web interactions and external sites.
From the tool's definition Start W3C WebDriver session, Chrome, Firefox, Safari
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs selenium_start 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 selenium_start, this is the rule to start with:
selenium_start 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 selenium_start call is checked against it from then on.
Questions about selenium_start
Start a first-class W3C WebDriver session on this runtime host. Supports Chrome, Firefox, and real Safari (macOS with safaridriver enabled). Does not bypass CAPTCHA or site auth; hand off to the user when needed. 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.
selenium_start accepts 9 parameters: url, width, height, record, browser, headful, profile, session_id, record_seconds. 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 selenium_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.
selenium_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 selenium_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 selenium_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.
selenium_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.
More on Yaver, and thousands of servers like it.
Across the catalogue