Get granular per-request usage events with model, token counts, costs, and whether the request was chargeable. Supports filtering by user email and date range.
AI agents call get_usage_events to retrieve information from Cursor Usage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves analytics data (model usage, token counts, costs, chargeability status) with filtering capabilities. It performs no mutations, deletions, code execution, or financial transactions. The data returned is observational billing/usage metadata. While the data could be sensitive (usage patterns, costs), the action itself is a non-destructive read operation.
From the tool's definition Tool name 'get_usage_events' and description 'Get granular per-request usage events' clearly indicate a retrieval operation. The phrase 'Supports filtering by user email and date range' confirms it queries existing data without modification or side effects.
Attacks that exploit this kind of access
Get granular per-request usage events with model, token counts, costs, and whether the request was chargeable. Supports filtering by user email and date range. It is categorised as a Read tool in the Cursor Usage MCP Server, which means it retrieves data without modifying state.
Register the Cursor Usage MCP server in PolicyLayer and add a rule for get_usage_events: 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 Cursor Usage. Nothing to install.
get_usage_events 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 get_usage_events 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 get_usage_events. 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.
get_usage_events is provided by the Cursor Usage MCP server (ofershap/cursor-usage). 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 →