AI agents call get_content to retrieve information from Browserless MCP 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 webpage content (HTML) without creating, modifying, or deleting data. It is a read-only operation similar to fetching or querying information. While the broader Browserless server includes Execute tools (execute_function, execute_browserql) and Destructive capabilities (download_files could enable data exfiltration), this specific tool is limited to passive content extraction.
From the tool's definition Tool name 'get_content' and description 'Extract rendered HTML content from a webpage' indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browserless MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_content:
{
"version": "1",
"default": "deny",
"tools": {
"get_content": {}
}
}get_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.
Extract rendered HTML content from a webpage. It is categorised as a Read tool in the Browserless MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Browserless MCP Server MCP server in PolicyLayer and add a rule for 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 Browserless MCP Server. Nothing to install.
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 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 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.
get_content is provided by the Browserless MCP Server MCP server (lizzard-solutions/browserless-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Browserless 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.
16 Browserless MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.