Critical Risk →

buffer_cut

Cut lines from file to buffer (copy and delete from source)

How to control buffer_cut ↓

What buffer_cut does on Clippy

AI agents call buffer_cut to permanently remove resources in Clippy — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why buffer_cut needs a policy

This tool performs an irreversible deletion of file content (the 'cut' operation removes lines from the source file). Although the content is placed in a buffer, the original data is permanently removed from the file. This is a destructive operation that cannot be undone by the tool itself.

From the tool's definition 'Cut lines from file to buffer (copy and delete from source)' - the tool irreversibly deletes content from the source file as part of its operation.

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

How to control buffer_cut

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

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

buffer_cut 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 Clippy — 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.

Related tools and policies

Go deeper

Questions about buffer_cut

What does the buffer_cut tool do? +

Cut lines from file to buffer (copy and delete from source). It is categorised as a Destructive tool in the Clippy 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 buffer_cut? +

Register the Clippy MCP server in PolicyLayer and add a rule for buffer_cut: 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 Clippy. Nothing to install.

What risk level is buffer_cut? +

buffer_cut 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 buffer_cut? +

Yes. Add a rate_limit block to the buffer_cut 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 buffer_cut completely? +

Set action: deny in the PolicyLayer policy for buffer_cut. 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 buffer_cut? +

buffer_cut is provided by the Clippy MCP server (neilberkman/clippy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Clippy tool call.

Start from Clippy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

7 Clippy tools catalogued and risk-classified — across an index of 43,000+ 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.