Get plan mode adoption: which models are being used in plan mode and how often.
AI agents call get_plans 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 and reports usage analytics about plan mode adoption across models. It queries existing data without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—worst case an agent reads analytics data it shouldn't have access to, but cannot alter billing, spending, or system state.
From the tool's definition Tool name 'get_plans' and description 'Get plan mode adoption' indicate data retrieval with no modification capability.
Attacks that exploit this kind of access
Get plan mode adoption: which models are being used in plan mode 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_plans: 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_plans 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_plans 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_plans. 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_plans 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 →