【内网/内部用户】查询内部用户详情、关联 key、累计 token/spend 用量。员工可查自己，管理员可查任意用户。关键词：我的账号、用户用量、内部用户信息
AI agents call litellm_user_info 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 user information including associated API keys and spend data — a read operation with no side effects. However, the exposure of API keys and financial spend data elevates severity to medium, as misuse could reveal sensitive credentials or usage patterns of internal users.
From the tool's definition 查询内部用户详情、关联 key、累计 token/spend 用量 (query internal user details, associated keys, cumulative token/spend usage)
Attacks that exploit this kind of access
【内网/内部用户】查询内部用户详情、关联 key、累计 token/spend 用量。员工可查自己，管理员可查任意用户。关键词：我的账号、用户用量、内部用户信息. 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_user_info: 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_user_info 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_user_info 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_user_info. 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_user_info 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 →