Delete a repository.
AI agents call repository_delete to permanently remove resources in Semaphore — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a repository and cannot be undone. It matches the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone (delete, drop, purge, force-push).' While Write operations are reversible, deletion is not.
From the tool's definition Tool name 'repository_delete' combined with description 'Delete a repository' indicates irreversible deletion of data.
Attacks that exploit this kind of access
Delete a repository. It is categorised as a Destructive tool in the Semaphore MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Semaphore MCP server in PolicyLayer and add a rule for repository_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 Semaphore. Nothing to install.
repository_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 repository_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 repository_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.
repository_delete is provided by the Semaphore MCP server (vitexsoftware/semaphore-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
repository_delete is one line of Semaphore's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →