Clean up stale task branches from interrupted runs.
AI agents call cleanup_stale_branches to permanently remove resources in Code Intelligence MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Branch cleanup removes git branches that cannot be easily recovered once deleted, especially if they were from interrupted runs and may not be backed up elsewhere. This is an irreversible destructive operation with potentially high blast radius if it incorrectly identifies branches as stale.
From the tool's definition 'Clean up stale task branches from interrupted runs' — deleting/removing branches is irreversible
Attacks that exploit this kind of access
Clean up stale task branches from interrupted runs. It is categorised as a Destructive tool in the Code Intelligence MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Code Intelligence MCP Server MCP server in PolicyLayer and add a rule for cleanup_stale_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 Code Intelligence MCP Server. Nothing to install.
cleanup_stale_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_stale_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_stale_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_stale_branches is provided by the Code Intelligence MCP Server MCP server (tech-spoke/llm-helper). 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 →