litellm_key_generate · Litellm Admin MCP: Risk & Policy

WHAT IT DOES

What litellm_key_generate does on Litellm Admin

AI agents use litellm_key_generate 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_key_generate needs a policy

This tool creates new API keys/credentials that enable access to internal LLM services. While not destructive (keys can be revoked) and not financial, this is a Write operation (creates credentials reversibly). Severity is high because misuse could allow an agent to provision excessive API keys, grant unauthorized access to internal LLM resources, or create credentials for malicious actors.

From the tool's definition Tool generates and returns API keys (virtual_key, sk-*) for employees to access internal LLM services. The description states it creates internal API access credentials that are returned only once, indicating this is a credential creation and provisioning…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

litellm_key_generate Rate-limited

litellm_key_generate 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_key_generate": {
      "limits": [
        {
          "counter": "litellm_key_generate_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_key_generate

What does the litellm_key_generate tool do? +

【内网/内部 API Key】为员工创建内网 LLM 访问密钥（飞书 bot 私聊开通场景）。返回 virtual_key（完整 sk-*，仅一次）及 onboarding 快速上手教程（BASE_URL、curl 测模型/推理）。关键词：申请api key、开通密钥、生成key、飞书bot、内网大模型. 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_key_generate? +

Register the Litellm Admin MCP server in PolicyLayer and add a rule for litellm_key_generate: 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_key_generate? +

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

Can I rate-limit litellm_key_generate? +

Yes. Add a rate_limit block to the litellm_key_generate 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_key_generate completely? +

Set action: deny in the PolicyLayer policy for litellm_key_generate. 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_key_generate? +

litellm_key_generate 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.