Clear the editor
AI agents call clear to permanently remove resources in Filopastry — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing an editor removes all current content without the ability to undo (in an automated agent context). This is analogous to overwriting/deleting data, making it Destructive. Severity is medium since it affects only the current editor session content rather than persistent stored data, but could cause loss of in-progress compositions.
From the tool's definition 'Clear the editor' implies removing/wiping the current editor content, which is an irreversible action that would destroy any unsaved work in the editor.
Attacks that exploit this kind of access
Clear the editor. It is categorised as a Destructive tool in the Filopastry MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Filopastry MCP server in PolicyLayer and add a rule for clear: 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 Filopastry. Nothing to install.
clear 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 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. 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 is provided by the Filopastry MCP server (youwenshao/filopastry). 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 →