Manage git branches (create, switch, list, delete)
AI agents call git_branch_manager to permanently remove resources in Claude MCP Server Integration — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly includes 'delete' as one of its operations, which can irreversibly remove git branches and their associated commit history (especially if the branch hasn't been merged). While 'create', 'switch', and 'list' are lower-risk operations, the presence of 'delete' elevates the classification to Destructive per the rule to pick the most severe applicable category.
From the tool's definition Manage git branches (create, switch, list, delete)
Attacks that exploit this kind of access
Manage git branches (create, switch, list, delete). It is categorised as a Destructive tool in the Claude MCP Server Integration MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude MCP Server Integration MCP server in PolicyLayer and add a rule for git_branch_manager: 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 Claude MCP Server Integration. Nothing to install.
git_branch_manager 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_branch_manager 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_branch_manager. 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_branch_manager is provided by the Claude MCP Server Integration MCP server (mokemoke0821/claude-mcp-integration). 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 →