browser.extract_html

Extract outerHTML from a selector.

Server MCP Playwright Browser mhrnqaruni/mcp-playwright-browser
Category Read
Risk class Low
Parameters 00 required

What browser.extract_html does on MCP Playwright Browser

AI agents call browser.extract_html to retrieve information from MCP Playwright Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why browser.extract_html needs a policy

This tool queries and retrieves HTML data from the DOM based on a CSS selector, producing no side effects or state changes. It is a passive data extraction operation that falls clearly within the Read category. Severity is low because HTML extraction alone poses minimal risk—the extracted data depends on what the user is accessing, but the tool itself cannot delete data, execute arbitrary code, or move money.

From the tool's definition Tool name 'extract_html' and description 'Extract outerHTML from a selector' indicates retrieval of HTML content from a web page without modification or execution of code.

Questions about browser.extract_html

What does the browser.extract_html tool do? +

Extract outerHTML from a selector. It is categorised as a Read tool in the MCP Playwright Browser MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browser.extract_html? +

Register the MCP Playwright Browser MCP server in PolicyLayer and add a rule for browser.extract_html: 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 MCP Playwright Browser. Nothing to install.

What risk level is browser.extract_html? +

browser.extract_html is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit browser.extract_html? +

Yes. Add a rate_limit block to the browser.extract_html 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.

How do I block browser.extract_html completely? +

Set action: deny in the PolicyLayer policy for browser.extract_html. 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.

What MCP server provides browser.extract_html? +

browser.extract_html is provided by the MCP Playwright Browser MCP server (mhrnqaruni/mcp-playwright-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.