selenium_text
Extract visible text from a CSS selector in the Selenium page. Defaults to body.
This record as markdown: /tools/io-github-kivanccakmak-yaver/selenium-text.md
What selenium_text does on Yaver
AI agents call selenium_text to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
selector | string | — | CSS selector, default body |
session_id | string | Yes | Selenium session ID |
Parameters from the server's own tool schema.
Why selenium_text is rated Low
This tool reads DOM content and returns text without modifying state, executing commands, or affecting external systems. The capability is limited to observation of rendered page content, making it a Read operation with low severity—misuse would only expose information already visible in the browser.
From the tool's definition Tool performs text extraction from a CSS selector with no side effects. Description states 'Extract visible text' and 'Defaults to body', indicating a retrieval operation.
Attacks that exploit this kind of access
The rule that runs selenium_text 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_text, this is the rule to start with:
selenium_text is read-only, so it stays allowed. 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_text call is checked against it from then on.
Questions about selenium_text
Extract visible text from a CSS selector in the Selenium page. Defaults to body. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
selenium_text accepts 2 parameters: selector, session_id. Required: session_id. 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_text: 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_text is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the selenium_text 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_text. 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_text 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.
This server
Across the catalogue