Outputs the HTML of elements that deeply contain the given search query. Elements that don
AI agents call search_html to retrieve information from Autoconsent MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches HTML structure from a web page to find elements matching a query. It performs no modifications, deletions, or code execution—only data retrieval. The truncated description ('Elements that don...') appears incomplete but does not suggest any write, execute, or destructive operations. Searching HTML is a pure query operation with no side effects.
From the tool's definition Tool name is 'search_html' and description indicates it 'Outputs the HTML of elements that deeply contain the given search query'. The verb 'Outputs' and the read-only nature of querying/retrieving HTML content without modification.
Attacks that exploit this kind of access
Outputs the HTML of elements that deeply contain the given search query. Elements that don. It is categorised as a Read tool in the Autoconsent MCP MCP Server, which means it retrieves data without modifying state.
Register the Autoconsent MCP server in PolicyLayer and add a rule for search_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 Autoconsent MCP. Nothing to install.
search_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 search_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 search_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.
search_html is provided by the Autoconsent MCP server (noisysocks/autoconsent-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 →