Clear both the visible screen and the scrollback buffer.
AI agents call clear_buffer to permanently remove resources in Iterm2 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing the scrollback buffer is an irreversible action — once the terminal history is erased, it cannot be recovered. This permanently destroys potentially important command history and output logs. The visible screen clear alone might be considered reversible, but the scrollback buffer purge makes this Destructive. Misuse by an AI agent could cause loss of critical terminal output or logs needed for debugging.
From the tool's definition Clear both the visible screen and the scrollback buffer
Attacks that exploit this kind of access
Clear both the visible screen and the scrollback buffer. It is categorised as a Destructive tool in the Iterm2 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Iterm2 MCP server in PolicyLayer and add a rule for clear_buffer: 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 Iterm2. Nothing to install.
clear_buffer 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 clear_buffer 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 clear_buffer. 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.
clear_buffer is provided by the Iterm2 MCP server (lorencarvalho/iterm2-mcp). 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 →