AI agents call browser_get_html to retrieve information from Abrasio 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 a webpage or DOM element. It performs a read-only query operation with no capability to modify state, execute code, delete data, or commit financial actions. The blast radius is minimal—an AI agent using this tool can only passively inspect webpage structure and content.
From the tool's definition Tool name is 'browser_get_html' and description states 'Get the inner HTML of an element', which retrieves data without modification or side effects.
Attacks that exploit this kind of access
Get the inner HTML of an element. Defaults to the full page body. It is categorised as a Read tool in the Abrasio MCP Server, which means it retrieves data without modifying state.
Register the Abrasio MCP server in PolicyLayer and add a rule for browser_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 Abrasio. Nothing to install.
browser_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 browser_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 browser_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.
browser_get_html is provided by the Abrasio MCP server (scrape-technology/abrasio-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 →