【内网/token用量】按天查看用户 token/spend 活动趋势。适用于:用量走势、周报。关键词:每日用量、用户token统计、活动报表
AI agents call litellm_usage_user_activity 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/queries usage data (token and spend activity) for users on a per-day basis. It is a read-only reporting/analytics tool with no side effects. Misuse risk is low — it may expose spend and usage data, but cannot modify or delete anything.
From the tool's definition 按天查看用户 token/spend 活动趋势 (view daily user token/spend activity trends); 适用于:用量走势、周报 (use cases: usage trends, weekly reports)
Attacks that exploit this kind of access
【内网/token用量】按天查看用户 token/spend 活动趋势。适用于:用量走势、周报。关键词:每日用量、用户token统计、活动报表. 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_usage_user_activity: 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_usage_user_activity 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_usage_user_activity 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_usage_user_activity. 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_usage_user_activity 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 →