AI agents invoke puppeteer_emulate_device to trigger actions in MCP-pptr. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a browser automation command that modifies the device context in which the browser operates. It is an Execute category tool because it triggers changes to browser state and execution environment.
From the tool's definition The tool name includes 'emulate_device' and the description states it 'Emulate mobile devices using Chrome DevTools Device Mode.' This invokes browser automation that changes the execution context and behavior of subsequent browser operations.
Attacks that exploit this kind of access
Emulate mobile devices using Chrome DevTools Device Mode. It is categorised as a Execute tool in the MCP-pptr MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP-pptr MCP server in PolicyLayer and add a rule for puppeteer_emulate_device: 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-pptr. Nothing to install.
puppeteer_emulate_device is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the puppeteer_emulate_device 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_emulate_device. 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_emulate_device is provided by the MCP-pptr MCP server (ringotc/mcp-pptr). 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 →