Get MCP (Model Context Protocol) tool usage: which MCP servers and tools are being used, and how often.
AI agents call get_mcp_usage 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 historical usage analytics without side effects. It queries which MCP tools have been used and usage frequency, consistent with a metrics/reporting function. No data is created, modified, deleted, or executed—it is purely a data retrieval operation fitting the Read category.
From the tool's definition Tool name 'get_mcp_usage' and description states 'Get MCP...tool usage' indicating data retrieval. Sibling tools all use 'get_' prefix (get_agent_edits, get_billing_groups, get_daily_usage, get_model_usage, etc.), which are typical Read patterns.
Attacks that exploit this kind of access
Get MCP (Model Context Protocol) tool usage: which MCP servers and tools 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_mcp_usage: 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_mcp_usage 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_mcp_usage 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_mcp_usage. 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_mcp_usage 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 →