cleanup_branches
AI agents call cleanup_branches to permanently remove resources in Unlimited — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'cleanup_branches' strongly implies deleting or removing git branches, which is a destructive and potentially irreversible operation (especially for remote branches). In the context of a server that uses git worktree isolation, branch cleanup likely removes worktrees and/or branches. However, the empty description lowers confidence significantly.
From the tool's definition Tool name 'cleanup_branches' — description is empty and uninformative.
Attacks that exploit this kind of access
cleanup_branches. It is categorised as a Destructive tool in the Unlimited MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Unlimited MCP server in PolicyLayer and add a rule for cleanup_branches: 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 Unlimited. Nothing to install.
cleanup_branches 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 cleanup_branches 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 cleanup_branches. 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.
cleanup_branches is provided by the Unlimited MCP server (triumsebas/unlimited-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 →