AI agents call get_all_content to retrieve information from Playwright MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation—it fetches and returns the HTML structure and content of an open webpage without side effects. While classified as Read (lowest severity among data operations), severity is elevated to 'medium' because: (1) retrieved page content may include sensitive information (credentials, API keys, personal data, authentication tokens), and (2) in an AI agent context, unrestricted access…
From the tool's definition Tool name 'get_all_content' and description indicate retrieval of page content in HTML format. No modification, deletion, or execution of code/commands occurs. The tool retrieves data about the current browser page state.
Documented attack patterns abuse exactly the kind of access get_all_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_all_content:
{
"version": "1",
"default": "deny",
"tools": {
"get_all_content": {}
}
}get_all_content is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
現在開いているページのコンテンツを取得し、HTML構造を保持した形式で返します. It is categorised as a Read tool in the Playwright MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP Server MCP server in PolicyLayer and add a rule for get_all_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 Server. Nothing to install.
get_all_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_all_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_all_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_all_content is provided by the Playwright MCP Server MCP server (showfive/playwright-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Playwright MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.