Extract all content from the current page
AI agents call puppeteer_get_content to retrieve information from Steel Puppeteer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/extracts page content without modifying state, placing it in the Read category. Severity is medium rather than low because extracted content could be sensitive (credentials, PII, API keys) depending on what the browser has loaded, and an agent could misuse it to exfiltrate information from pages the user visits.
From the tool's definition Tool name 'puppeteer_get_content' and description 'Extract all content from the current page' indicate data retrieval with no modification or execution of side effects.
Attacks that exploit this kind of access
Extract all content from the current page. It is categorised as a Read tool in the Steel Puppeteer MCP Server, which means it retrieves data without modifying state.
Register the Steel Puppeteer MCP server in PolicyLayer and add a rule for puppeteer_get_content: 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 Steel Puppeteer. Nothing to install.
puppeteer_get_content 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_get_content 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_get_content. 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_get_content is provided by the Steel Puppeteer MCP server (rdvo/mcp-server). 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 →