Critical Risk →

delete_all_bookmarks

DESTRUCTIVE AND IRREVERSIBLE: Permanently deletes ALL bookmarks one by one. This cannot be undone. Always confirm explicitly with the user before calling this tool.

How to control delete_all_bookmarks ↓

AI agents call delete_all_bookmarks to permanently remove resources in X (Twitter) MCP server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

This tool removes data that cannot be recovered. Although the blast radius is limited to a user's bookmarks (not system-wide data), the irreversible nature and the scale ('ALL bookmarks') make it a destructive operation. The explicit warning in the description confirms the risk severity is high rather than medium.

From the tool's definition Tool description explicitly states 'DESTRUCTIVE AND IRREVERSIBLE: Permanently deletes ALL bookmarks one by one. This cannot be undone.' The verb 'deletes' combined with 'IRREVERSIBLE' and 'cannot be undone' are unambiguous markers of destructive operations.

Documented attack patterns abuse exactly the kind of access delete_all_bookmarks gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and X (Twitter) MCP server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_all_bookmarks:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_all_bookmarks"
  ]
}

delete_all_bookmarks disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register X (Twitter) MCP server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Go deeper

What does the delete_all_bookmarks tool do? +

DESTRUCTIVE AND IRREVERSIBLE: Permanently deletes ALL bookmarks one by one. This cannot be undone. Always confirm explicitly with the user before calling this tool. It is categorised as a Destructive tool in the X (Twitter) MCP server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_all_bookmarks? +

Register the X (Twitter) MCP server MCP server in PolicyLayer and add a rule for delete_all_bookmarks: 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 X (Twitter) MCP server. Nothing to install.

What risk level is delete_all_bookmarks? +

delete_all_bookmarks is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_all_bookmarks? +

Yes. Add a rate_limit block to the delete_all_bookmarks 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.

How do I block delete_all_bookmarks completely? +

Set action: deny in the PolicyLayer policy for delete_all_bookmarks. 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.

What MCP server provides delete_all_bookmarks? +

delete_all_bookmarks is provided by the X (Twitter) MCP server MCP server (rafaljanicki/x-twitter-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every X (Twitter) MCP server tool call.

Deterministic rules across all 24 X (Twitter) MCP server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

24 X (Twitter) MCP server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.