AI agents call get_html to retrieve information from Browser Use Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns HTML content from a webpage, which is a read-only operation with no side effects. While the server enables browser automation and includes code execution capabilities (execute_js), this specific tool is limited to passive content retrieval. The blast radius is minimal—an AI agent retrieving HTML cannot modify data or trigger external actions through this tool alone.
From the tool's definition Tool name 'get_html' and description 'Get the HTML content of a webpage' indicate retrieval of page content without modification or code execution.
Documented attack patterns abuse exactly the kind of access get_html gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browser Use Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_html:
{
"version": "1",
"default": "deny",
"tools": {
"get_html": {}
}
}get_html 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.
Get the HTML content of a webpage. It is categorised as a Read tool in the Browser Use Server MCP Server, which means it retrieves data without modifying state.
Register the Browser Use Server MCP server in PolicyLayer and add a rule for get_html: 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 Browser Use Server. Nothing to install.
get_html 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_html 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_html. 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_html is provided by the Browser Use Server MCP server (ztobs/cline-browser-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Browser Use 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.
4 Browser Use Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.