删除GitHub仓库。请谨慎使用此功能，删除后无法恢复！
AI agents call github_delete_repo to permanently remove resources in MCP Toolkit — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes an entire GitHub repository—a destructive operation that cannot be undone. The description's explicit warning about non-recovery confirms the irreversible nature. This poses critical risk if an AI agent mistakenly targets the wrong repository or is manipulated into deletion via prompt injection.
From the tool's definition Tool name 'github_delete_repo' combined with description stating '删除GitHub仓库' (delete GitHub repository) and explicit warning '删除后无法恢复' (cannot be recovered after deletion)
Attacks that exploit this kind of access
删除GitHub仓库。请谨慎使用此功能，删除后无法恢复！. It is categorised as a Destructive tool in the MCP Toolkit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Toolkit MCP server in PolicyLayer and add a rule for github_delete_repo: 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 MCP Toolkit. Nothing to install.
github_delete_repo 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 github_delete_repo 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 github_delete_repo. 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.
github_delete_repo is provided by the MCP Toolkit MCP server (zxfgds/mcp-toolkit). 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 →