【内网/内部模型】管理员删除内网模型配置。参数 id 为 model_info.id。关键词：下线模型、删除内部模型（通常需 proxy_admin）
AI agents call litellm_model_delete to permanently remove resources in Litellm Admin — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes model configurations, which cannot be undone. Deletion of critical infrastructure models could disrupt service availability. While not as severe as financial transactions, the irreversible nature and potential blast radius (service disruption) warrant 'high' severity. Confidence is high due to explicit 'delete' semantics and administrative context.
From the tool's definition Tool name contains 'delete'; description states '删除内部模型' (delete internal model) and '下线模型' (take model offline). The description indicates this irreversibly removes model configurations from the system.
Attacks that exploit this kind of access
【内网/内部模型】管理员删除内网模型配置。参数 id 为 model_info.id。关键词：下线模型、删除内部模型（通常需 proxy_admin）. It is categorised as a Destructive tool in the Litellm Admin MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Litellm Admin MCP server in PolicyLayer and add a rule for litellm_model_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 Litellm Admin. Nothing to install.
litellm_model_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 litellm_model_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 litellm_model_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.
litellm_model_delete is provided by the Litellm Admin MCP server (junwayne66/litellm-admin-mcp). 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 →