Add, list, or remove worktrees.
AI agents call git_worktree to permanently remove resources in Git — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool supports three operations: add (Write), list (Read), and remove (Destructive). Per the most-severe-wins rule, the presence of a remove operation that irreversibly deletes worktrees elevates the classification to Destructive. Severity is high because an AI agent could remove active worktrees containing uncommitted work, causing data loss.
From the tool's definition 'remove worktrees' — removing a worktree is an irreversible deletion of a working tree path and its associated state
Attacks that exploit this kind of access
Add, list, or remove worktrees. It is categorised as a Destructive tool in the Git MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Git MCP server in PolicyLayer and add a rule for git_worktree: 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 Git. Nothing to install.
git_worktree 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 git_worktree 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 git_worktree. 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.
git_worktree is provided by the Git MCP server (selfagency/git-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 →