Get the current page HTML content
AI agents call get_page_content to retrieve information from Playwright MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves HTML content from the current browser page, which is a read-only operation with no side effects. While the Playwright server enables browser automation (which could be misused), this specific tool merely fetches data. The severity is low because obtaining page HTML is non-destructive and does not expose sensitive controls like financial systems or irreversible operations.
From the tool's definition Tool name 'get_page_content' and description 'Get the current page HTML content' indicate a retrieval operation that reads DOM content without modifying state or triggering external effects.
Attacks that exploit this kind of access
Get the current page HTML content. It is categorised as a Read tool in the Playwright MCP MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP server in PolicyLayer and add a rule for get_page_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 Playwright MCP. Nothing to install.
get_page_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 get_page_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 get_page_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.
get_page_content is provided by the Playwright MCP server (misanthropic-ai/playwrite-mcp). 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 →