【内网/token用量】查询内网 LLM 调用的 token 消耗与 spend 明细日志。适用于：员工查自己的用量、管理员按 user_id/api_key 排查账单。关键词：token用量、消耗、调用记录、spend、用量报表
AI agents call litellm_usage_spend_logs 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 spend logs and token usage data — a read-only operation with no side effects. Severity is medium because spend logs may contain sensitive financial and usage information about users and API keys, making unauthorized access a meaningful risk, but it does not modify or delete any data.
From the tool's definition 查询内网 LLM 调用的 token 消耗与 spend 明细日志 (queries internal LLM call token consumption and spend detail logs)
Attacks that exploit this kind of access
【内网/token用量】查询内网 LLM 调用的 token 消耗与 spend 明细日志。适用于：员工查自己的用量、管理员按 user_id/api_key 排查账单。关键词：token用量、消耗、调用记录、spend、用量报表. 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_spend_logs: 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_spend_logs 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_spend_logs 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_spend_logs. 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_spend_logs 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 →