AI agents invoke puppeteer_devtools_subscribe 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.
Subscribing to CDP events allows an AI agent to observe and react to browser events in real-time, potentially enabling complex automated interactions or detection of sensitive information (e.g., network requests, credentials in console, DOM changes). Although the subscription itself is read-like, it is a foundational capability for executing sophisticated browser automation workflows.
From the tool's definition Tool name 'puppeteer_devtools_subscribe' combined with description 'Subscribe to CDP events' indicates subscription to Chrome DevTools Protocol (CDP) events.
Attacks that exploit this kind of access
Subscribe to CDP events. 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_devtools_subscribe: 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_devtools_subscribe 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_devtools_subscribe 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_devtools_subscribe. 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_devtools_subscribe 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 →