Delete a temporary clone created by
AI agents call repo_cleanup to permanently remove resources in Kubesearch — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool deletes 'temporary' clones (suggesting limited scope and reversibility through re-cloning), the action itself is a permanent deletion that cannot be undone without re-executing repo_clone. The incomplete description weakens confidence slightly, but the word 'Delete' combined with the tool's purpose clearly indicates a Destructive operation.
From the tool's definition Tool name 'repo_cleanup' with description 'Delete a temporary clone created by' indicates deletion of cloned repository data. This is an irreversible removal operation, matching the Destructive category definition.
Attacks that exploit this kind of access
Delete a temporary clone created by. It is categorised as a Destructive tool in the Kubesearch MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kubesearch MCP server in PolicyLayer and add a rule for repo_cleanup: 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 Kubesearch. Nothing to install.
repo_cleanup 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 repo_cleanup 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 repo_cleanup. 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.
repo_cleanup is provided by the Kubesearch MCP server (perfectra1n/kubesearch-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 →