litellm_model_update · Litellm Admin MCP: Risk & Policy

WHAT IT DOES

What litellm_model_update does on Litellm Admin

AI agents use litellm_model_update 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.

WHY IT NEEDS A POLICY

Why litellm_model_update needs a policy

This tool modifies model parameters (api_base, model mapping, budget settings) which are configuration changes. While these could have operational impact on LLM proxy routing and cost control, they are reversible updates rather than irreversible deletions or financial transactions.

From the tool's definition Tool name 'litellm_model_update' and description stating '管理员更新内网模型参数（api_base、model 映射、预算等）' (admin updates internal model parameters including api_base, model mapping, budgets, etc.). These are reversible modifications to model configuration.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

litellm_model_update Rate-limited

litellm_model_update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "litellm_model_update": {
      "limits": [
        {
          "counter": "litellm_model_update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Litellm Admin, so you can run agents against it safely.

FAQ

Questions about litellm_model_update

What does the litellm_model_update tool do? +

【内网/内部模型】管理员更新内网模型参数（api_base、model 映射、预算等）。关键词：修改模型、内部模型配置（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.

How do I enforce a policy on litellm_model_update? +

Register the Litellm Admin MCP server in PolicyLayer and add a rule for litellm_model_update: 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.

What risk level is litellm_model_update? +

litellm_model_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit litellm_model_update? +

Yes. Add a rate_limit block to the litellm_model_update 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.

How do I block litellm_model_update completely? +

Set action: deny in the PolicyLayer policy for litellm_model_update. 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.

What MCP server provides litellm_model_update? +

litellm_model_update 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.