browser_cookie_delete
AI agents call browser_cookie_delete to permanently remove resources in Playwright MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting cookies is an irreversible action that removes stored session/authentication data from the browser. While cookies can be recreated, the deletion itself cannot be undone and may cause session loss or authentication failures. The empty description lowers confidence, but the name strongly implies destructive behavior consistent with sibling tools like browser_cookie_clear.
From the tool's definition Tool name 'browser_cookie_delete' implies deletion of browser cookies; description is empty providing no additional context.
Attacks that exploit this kind of access
browser_cookie_delete. It is categorised as a Destructive tool in the Playwright MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_cookie_delete: 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 Playwright MCP. Nothing to install.
browser_cookie_delete 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 browser_cookie_delete 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_cookie_delete. 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_cookie_delete is provided by the Playwright MCP server (roshan571/playwright-mcp2). 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 →