当用户明确要求删除普通分支时调用。
AI agents call delete_branch to permanently remove resources in GitBranchMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete_branch tool performs irreversible deletion of branch records/data, which is the defining characteristic of the Destructive category. While the blast radius is somewhat limited to a single branch context (not full system destruction), the operation cannot be undone and could result in loss of programming notes or decision logs.
From the tool's definition Tool name is 'delete_branch' and description indicates it deletes branches when explicitly requested by the user.
Attacks that exploit this kind of access
当用户明确要求删除普通分支时调用。. It is categorised as a Destructive tool in the GitBranchMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitBranch MCP server in PolicyLayer and add a rule for delete_branch: 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 GitBranchMCP. Nothing to install.
delete_branch 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 delete_branch 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 delete_branch. 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.
delete_branch is provided by the GitBranch MCP server (lianggaoyuan/gitbranchmcp). 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 →