Remove a bookmark by its ID. CASCADE DELETES all child bookmarks. STOP! Before removing, ask yourself: 1. Can I UPDATE this bookmark instead? (update_bookmark) 2. Did I verify the bookmark content first? (get_bookmark) 3. Am I aware this will delete ALL child bookmarks? Only remove a bookmark whe...
AI agents call remove_bookmark to permanently remove resources in MCP Bookmarks — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes data (bookmarks and all nested children) with no undo capability or recovery mechanism. This is irreversible data loss, making it Destructive rather than Write. The cautionary prompt warns users to verify content first and consider alternatives (update vs delete), underscoring the severity.
From the tool's definition Tool description explicitly states 'Remove a bookmark by its ID. CASCADE DELETES all child bookmarks.' The cascade deletion behavior and irreversible nature of the operation (bookmarks cannot be recovered after removal) classify this as destructive.
Attacks that exploit this kind of access
Remove a bookmark by its ID. CASCADE DELETES all child bookmarks. STOP! Before removing, ask yourself: 1. Can I UPDATE this bookmark instead? (update_bookmark) 2. Did I verify the bookmark content first? (get_bookmark) 3. Am I aware this will delete ALL child bookmarks? Only remove a bookmark when it is truly no longer needed. For bulk removal, use batch_remove_bookmarks. It is categorised as a Destructive tool in the MCP Bookmarks MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Bookmarks MCP server in PolicyLayer and add a rule for remove_bookmark: 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 MCP Bookmarks. Nothing to install.
remove_bookmark 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 remove_bookmark 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 remove_bookmark. 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.
remove_bookmark is provided by the MCP Bookmarks MCP server (linonon/mcpbookmarks). 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 →