Delete bookmarks
AI agents call chrome_bookmark_delete to permanently remove resources in Chrome MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes bookmarks, which cannot be easily recovered and represents a destructive action on user data. While the blast radius is somewhat contained (affects only bookmarks, not system-level data), the irreversible nature and potential for loss of important saved references warrants a 'high' severity rating. Confidence is high because the intent is unambiguous.
From the tool's definition Tool name 'chrome_bookmark_delete' combined with description 'Delete bookmarks' explicitly performs irreversible deletion of user data.
Attacks that exploit this kind of access
Delete bookmarks. It is categorised as a Destructive tool in the Chrome MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for chrome_bookmark_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 Chrome MCP Server. Nothing to install.
chrome_bookmark_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 chrome_bookmark_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 chrome_bookmark_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.
chrome_bookmark_delete is provided by the Chrome MCP Server MCP server (standbyme626/mcp-chrome). 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 →