Reset browser data including cookies, cache, localStorage, and sessionStorage
AI agents call reset_browser_data to permanently remove resources in Autoconsent MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly clears persistent browser state — cookies, cache, localStorage, and sessionStorage — which cannot be recovered after deletion. This is a destructive operation with a broad blast radius, as it removes all stored credentials, session tokens, and site data in the browser environment.
From the tool's definition Reset browser data including cookies, cache, localStorage, and sessionStorage
Attacks that exploit this kind of access
Reset browser data including cookies, cache, localStorage, and sessionStorage. It is categorised as a Destructive tool in the Autoconsent MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Autoconsent MCP server in PolicyLayer and add a rule for reset_browser_data: 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.
reset_browser_data is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the reset_browser_data 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 reset_browser_data. 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.
reset_browser_data 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 →