browser_take_screenshot · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_take_screenshot does on Playwright MCP

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

WHY IT NEEDS A POLICY

Why browser_take_screenshot needs a policy

Taking a screenshot is a read-only operation that captures the current state of a web page for inspection. It has no side effects, does not modify data, execute code, delete anything, or move money. The blast radius if misused by an AI agent is minimal—it could only expose sensitive information visually present on screen, not alter system state.

From the tool's definition Tool name 'browser_take_screenshot' indicates screenshot capture; no description provided. Sibling tools on this server (browser_click, browser_drag, browser_fill_form, browser_evaluate, browser_file_upload) perform various actions, but screenshot capture…

Attacks that exploit this kind of access

Questions about browser_take_screenshot

What does the browser_take_screenshot tool do? +

browser_take_screenshot. It is categorised as a Read tool in the Playwright MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browser_take_screenshot? +

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

What risk level is browser_take_screenshot? +

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

Can I rate-limit browser_take_screenshot? +

Yes. Add a rate_limit block to the browser_take_screenshot 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_take_screenshot completely? +

Set action: deny in the PolicyLayer policy for browser_take_screenshot. 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_take_screenshot? +

browser_take_screenshot is provided by the Playwright MCP server (lysander72/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.