browser_pdf_save
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 creates or writes PDF files, which is a reversible modification of the filesystem. While not as severe as Destructive (files can be overwritten or deleted), it exceeds Read category since it produces artifacts. Severity is medium because uncontrolled PDF generation could fill disk space or export sensitive page content, but the impact is localized and reversible.
From the tool's definition Tool name 'browser_pdf_save' indicates saving/writing PDF files to disk. The sibling tools (browser_click, browser_evaluate, etc.) confirm this is a browser automation server capable of triggering actions with side effects.
Attacks that exploit this kind of access
browser_pdf_save. 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 (roshan571/playwright-mcp2). 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 →