Legge e restituisce il DOM HTML della pagina o di un elemento specifico
AI agents call read_dom to retrieve information from DOM Analyzer 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 DOM structure information. It performs no side effects, does not modify data, execute arbitrary operations, or delete content. It is a pure read operation analogous to inspecting page structure for testing or debugging purposes. Low severity due to limited blast radius—misuse would only expose frontend structure data already visible to users.
From the tool's definition Tool name 'read_dom' and description 'Legge e restituisce il DOM HTML della pagina o di un elemento specifico' (reads and returns the HTML DOM of the page or a specific element) indicate data retrieval without modification.
Attacks that exploit this kind of access
Legge e restituisce il DOM HTML della pagina o di un elemento specifico. It is categorised as a Read tool in the DOM Analyzer MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DOM Analyzer MCP Server MCP server in PolicyLayer and add a rule for read_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 DOM Analyzer MCP Server. Nothing to install.
read_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 read_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 read_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.
read_dom is provided by the DOM Analyzer MCP Server MCP server (sudo-elia/dom-analyzer-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 →