【内网/内部模型】管理员向 LiteLLM 代理新增内网模型路由。适用于:接入新大模型、扩容模型池。关键词:添加模型、内部模型、模型管理(通常需 proxy_admin)
AI agents use litellm_model_create to create or update resources in Litellm Admin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Litellm Admin environment.
This tool creates and adds new model configurations to the LiteLLM proxy system. It is a Write operation because it creates new resources (model routing configurations) that are reversible through deletion (litellm_model_delete exists as a sibling tool).
From the tool's definition Tool name 'litellm_model_create' and description indicating '新增内网模型路由' (add new internal model routing) and '添加模型' (add model). The description explicitly states this is for 'adding models' and 'model management' requiring proxy_admin privileges.
Attacks that exploit this kind of access
【内网/内部模型】管理员向 LiteLLM 代理新增内网模型路由。适用于:接入新大模型、扩容模型池。关键词:添加模型、内部模型、模型管理(通常需 proxy_admin). It is categorised as a Write tool in the Litellm Admin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Litellm Admin MCP server in PolicyLayer and add a rule for litellm_model_create: 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_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the litellm_model_create 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_create. 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_create 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 →