Get command usage analytics: which Cursor commands are being used and how often.
AI agents call get_commands 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 usage metrics about command invocations—a read-only query with no side effects. It poses minimal risk; the worst outcome of misuse would be exposure of aggregate usage statistics. There are no write, execute, destructive, or financial operations involved.
From the tool's definition Tool name 'get_commands' and description 'Get command usage analytics: which Cursor commands are being used and how often' indicate a query/retrieval operation with no modifications.
Attacks that exploit this kind of access
Get command usage analytics: which Cursor commands are being used and how often. 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_commands: 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_commands 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_commands 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_commands. 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_commands 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 →