Save page as PDF
AI agents use browser_pdf_save to create or update resources in Playwright MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Playwright MCP environment.
This tool generates and saves a PDF file from the current page content. It creates a new file on the filesystem, which is a Write operation. It is not Destructive (no deletion), not Execute (no code execution), and not Financial. Severity is medium because it could be used to exfiltrate page content as a file, but it requires the page to already be loaded and does not modify remote data.
From the tool's definition 'Save page as PDF' — creates a PDF file from the current browser page
Attacks that exploit this kind of access
Save page as PDF. It is categorised as a Write tool in the Playwright MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_pdf_save: 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.
browser_pdf_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the browser_pdf_save 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_pdf_save. 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_pdf_save is provided by the Playwright MCP server (lewisvoncken/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the 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 →