【内网/内部模型】查询公司内网 LiteLLM 代理上已配置的 LLM 模型列表、路由与参数。适用于：查看可用模型、飞书 bot 回答“有哪些模型”、员工选型。关键词：内网模型、模型列表、大模型、smart-router
AI agents call litellm_model_list to retrieve information from Litellm Admin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about configured models, routing, and parameters from an internal system. The description explicitly frames it as a query/list operation for viewing available models, which produces no modifications or destructive effects. It is a read-only information retrieval operation typical of admin dashboards.
From the tool's definition Tool name 'litellm_model_list' and description indicate querying/listing configured LLM models, routes and parameters on an internal LiteLLM proxy.
Attacks that exploit this kind of access
【内网/内部模型】查询公司内网 LiteLLM 代理上已配置的 LLM 模型列表、路由与参数。适用于：查看可用模型、飞书 bot 回答“有哪些模型”、员工选型。关键词：内网模型、模型列表、大模型、smart-router. It is categorised as a Read tool in the Litellm Admin MCP Server, which means it retrieves data without modifying state.
Register the Litellm Admin MCP server in PolicyLayer and add a rule for litellm_model_list: 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_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the litellm_model_list 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_list. 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_list 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.
litellm_model_list is one line of Litellm Admin'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 →