AI agents call get_dom to retrieve information from InSite 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 DOM/HTML content from a browser page. It has no side effects, does not modify data, execute code, delete content, or affect financial systems. The optional CSS selector parameter only filters what is retrieved, not what is modified. This is a standard Read category operation with low blast radius if misused by an AI agent—worst case being unintended information disclosure or scraping.
From the tool's definition Tool name 'get_dom' and description 'Get DOM content as HTML string, optionally filtered by CSS selector' clearly indicates retrieval of page content without modification.
Attacks that exploit this kind of access
Get DOM content as HTML string, optionally filtered by CSS selector. It is categorised as a Read tool in the InSite MCP Server, which means it retrieves data without modifying state.
Register the InSite MCP server in PolicyLayer and add a rule for get_dom: 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 InSite. Nothing to install.
get_dom 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_dom 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_dom. 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_dom is provided by the InSite MCP server (jowharshamshiri/insite). 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 →