worktree
Lists, adds, removes, locks, unlocks, or prunes git worktrees for managing multiple working trees. Returns structured data with worktree paths, branches, and HEAD commits.
This record as markdown: /tools/io-github-dave-london-github/worktree.md
What worktree does on Github
AI agents call worktree to permanently remove resources in Github, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why worktree is rated Critical
The tool supports removing and pruning git worktrees, which are irreversible destructive operations. Pruning deletes stale worktree administrative files, and removing a worktree deletes the working tree directory. Since the most severe applicable category applies, and 'remove'/'prune' operations cannot be undone, this is classified as Destructive.
From the tool's definition removes, locks, unlocks, or prunes git worktrees
Attacks that exploit this kind of access
The rule that runs worktree safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For worktree, this is the rule to start with:
worktree is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Github, apply this rule, and every worktree call is checked against it from then on.
Questions about worktree
Lists, adds, removes, locks, unlocks, or prunes git worktrees for managing multiple working trees. Returns structured data with worktree paths, branches, and HEAD commits. It is categorised as a Destructive tool in the Github MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Github MCP server in PolicyLayer and add a rule for 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 Github. Nothing to install.
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 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 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.
worktree is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
Across the catalogue