【内网/token用量】管理员查看全平台 spend 汇总报表（按日期/团队/用户分组）。关键词：全局用量、平台报表、token统计、费用汇总（通常需 proxy_admin）
AI agents call litellm_usage_global_report 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 aggregated spend/usage reports across the platform. It is a read-only query operation returning statistics grouped by date, team, or user. However, it exposes sensitive financial and organizational data (token usage, spend summaries, user/team breakdowns) to whoever invokes it, hence medium severity due to data sensitivity and admin-level access required.
From the tool's definition 管理员查看全平台 spend 汇总报表（按日期/团队/用户分组）
Attacks that exploit this kind of access
【内网/token用量】管理员查看全平台 spend 汇总报表（按日期/团队/用户分组）。关键词：全局用量、平台报表、token统计、费用汇总（通常需 proxy_admin）. 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_global_report: 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_global_report 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_global_report 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_global_report. 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_global_report 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 →