Remove a worktree
AI agents call treehouse_remove 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.
Removing a worktree irreversibly deletes local workspace state and files. While the underlying git repository may preserve history, the worktree's working directory and uncommitted changes are lost. This is a destructive, non-reversible action that fits the Destructive category more than Write.
From the tool's definition Tool name is 'treehouse_remove' with description 'Remove a worktree'. The word 'remove' applied to a git worktree is a destructive operation that deletes the worktree and its associated directories/files, which cannot be trivially undone without version…
Attacks that exploit this kind of access
Remove a worktree. 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_remove: 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_remove 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_remove 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_remove. 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_remove 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 →