Permanently delete a repository. Requires confirmation.
AI agents call repo_delete to permanently remove resources in Git Steer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a repository is an irreversible action that destroys all associated code, history, issues, pull requests, and configurations. This has massive blast radius—an AI agent with access to this tool could wipe out critical repositories, causing data loss and operational disruption. Even though confirmation is required, an autonomous agent could bypass or confirm destructively.
From the tool's definition Tool name is 'repo_delete' and description states 'Permanently delete a repository'. The word 'Permanently' and 'delete' are explicit indicators of irreversible data destruction.
Attacks that exploit this kind of access
Permanently delete a repository. Requires confirmation. It is categorised as a Destructive tool in the Git Steer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Git Steer MCP server in PolicyLayer and add a rule for repo_delete: 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 Steer. Nothing to install.
repo_delete 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 repo_delete 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 repo_delete. 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.
repo_delete is provided by the Git Steer MCP server (ry-ops/git-steer). 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 →