Remove old worktrees based on retention policy
AI agents call treehouse_clean to permanently remove resources in Treehouse Worktree — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes git worktrees based on a retention policy. While the operation may be partially reversible through git reflog in some cases, the intended behavior is permanent removal of working directories and their associated state.
From the tool's definition Tool name 'treehouse_clean' combined with description 'Remove old worktrees' indicates deletion of git worktrees. The sibling tool 'treehouse_remove' reinforces that this server manages destructive operations on worktrees.
Attacks that exploit this kind of access
Remove old worktrees based on retention policy. It is categorised as a Destructive tool in the Treehouse Worktree MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Treehouse Worktree MCP server in PolicyLayer and add a rule for treehouse_clean: 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 Treehouse Worktree. Nothing to install.
treehouse_clean 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 treehouse_clean 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 treehouse_clean. 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.
treehouse_clean is provided by the Treehouse Worktree MCP server (mark-hingston/treehouse-worktree). 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 →