【内网/内部 API Key】更新 virtual key 的模型权限、预算、限流等。关键词:修改api key、调整模型权限、密钥配置
AI agents use litellm_key_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.
This tool modifies API key configurations including permissions, budgets, and rate limits—a reversible write operation that alters system state and security controls. While it could enable unauthorized access escalation if misused by an agent, it is not inherently destructive (keys aren't deleted) or financial (no money movement), making Write the correct category.
From the tool's definition Tool description explicitly states '更新 virtual key' (update virtual key) with capabilities to modify '模型权限、预算、限流' (model permissions, budget, rate limiting).
Attacks that exploit this kind of access
【内网/内部 API Key】更新 virtual key 的模型权限、预算、限流等。关键词:修改api key、调整模型权限、密钥配置. 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_key_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.
litellm_key_update 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_key_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.
Set action: deny in the PolicyLayer policy for litellm_key_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.
litellm_key_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.
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 →