Clean up orphaned worktrees that no longer have active implementers. Call this during maintenance.
AI agents call worktree_cleanup to permanently remove resources in Lockstep — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cleaning up worktrees involves removing git worktrees and their associated working directories. This is an irreversible operation — once a worktree is deleted, any uncommitted or unsaved work in it is permanently lost. The term 'orphaned' suggests these are worktrees without active owners, but misidentification could destroy active work.
From the tool's definition 'Clean up orphaned worktrees' — cleanup operations that remove worktrees are irreversible deletions of workspace state
Attacks that exploit this kind of access
Clean up orphaned worktrees that no longer have active implementers. Call this during maintenance. It is categorised as a Destructive tool in the Lockstep MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lockstep MCP server in PolicyLayer and add a rule for worktree_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 Lockstep. Nothing to install.
worktree_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 worktree_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 worktree_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.
worktree_cleanup is provided by the Lockstep MCP server (tmmoore286/lockstep-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 →