Branch tool. Use action=list|create|delete|rename|checkout|set_upstream|recent for branch workflows.
AI agents call git_branches 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.
While the tool supports read-only actions like 'list' and 'recent', it also supports destructive operations like 'delete' (irreversibly removes a branch) and mutating operations like 'create', 'rename', 'checkout', and 'set_upstream'. Per the rules, we pick the most severe applicable category.
From the tool's definition action=list|create|delete|rename|checkout|set_upstream|recent — explicitly includes 'delete' action for branches
Attacks that exploit this kind of access
Branch tool. Use action=list|create|delete|rename|checkout|set_upstream|recent for branch workflows. 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_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 Git. Nothing to install.
git_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 git_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 git_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.
git_branches 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 →