AI agents call puppeteer_screenshot to retrieve information from Puppeteer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots are typically read/capture operations with no side effects. However, the empty description lowers confidence. Given the Puppeteer context (browser automation), a screenshot captures the current browser state without modifying it. Severity is medium because it could capture sensitive on-screen data.
From the tool's definition Tool name 'puppeteer_screenshot' suggests capturing a screenshot; no description provided to confirm or deny side effects.
Attacks that exploit this kind of access
puppeteer_screenshot. It is categorised as a Read tool in the Puppeteer MCP Server, which means it retrieves data without modifying state.
Register the Puppeteer MCP server in PolicyLayer and add a rule for puppeteer_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 Puppeteer. Nothing to install.
puppeteer_screenshot 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 puppeteer_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.
Set action: deny in the PolicyLayer policy for puppeteer_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.
puppeteer_screenshot is provided by the Puppeteer MCP server (@modelcontextprotocol/server-puppeteer). 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 →