Delete a GitHub repository
AI agents call delete_repository to permanently remove resources in GitHub MCP Tools — 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 removes all code, history, issues, pull requests, and associated data. This cannot be undone and represents permanent data loss. It is the most severe category applicable (Destructive > Execute > Write > Read), warranting a 'high' severity rating due to the significant blast radius if an AI agent mistakenly or maliciously deletes critical repositories.
From the tool's definition Tool name is 'delete_repository' and description states 'Delete a GitHub repository'. The verb 'delete' combined with the object 'repository' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a GitHub repository. It is categorised as a Destructive tool in the GitHub MCP Tools MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitHub MCP Tools MCP server in PolicyLayer and add a rule for delete_repository: 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 GitHub MCP Tools. Nothing to install.
delete_repository 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_repository 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_repository. 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_repository is provided by the GitHub MCP Tools MCP server (pranesh-2005/usingmcp). 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 →