get_model_usage

Get model usage breakdown per day: which models are being used, how many messages, and by how many users. Essential for understanding model adoption and cost drivers.

Server Cursor Usage ofershap/cursor-usage
Category Read
Risk class Low
Parameters 00 required

What get_model_usage does on Cursor Usage

AI agents call get_model_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.

Why get_model_usage needs a policy

This tool retrieves and queries analytics data (model adoption metrics, message counts, user counts) without any side effects. It performs a read-only operation on existing usage data. The sibling tools (all prefixed with 'get_') and server description (analytics/tracking) further confirm this is a read operation. No irreversible actions, code execution, financial transactions, or data modification occur.

From the tool's definition Tool name 'get_model_usage' and description 'Get model usage breakdown per day: which models are being used, how many messages, and by how many users.' indicates pure data retrieval with no modification, deletion, or execution capabilities.

Questions about get_model_usage

What does the get_model_usage tool do? +

Get model usage breakdown per day: which models are being used, how many messages, and by how many users. Essential for understanding model adoption and cost drivers. It is categorised as a Read tool in the Cursor Usage MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_model_usage? +

Register the Cursor Usage MCP server in PolicyLayer and add a rule for get_model_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.

What risk level is get_model_usage? +

get_model_usage is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_model_usage? +

Yes. Add a rate_limit block to the get_model_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.

How do I block get_model_usage completely? +

Set action: deny in the PolicyLayer policy for get_model_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.

What MCP server provides get_model_usage? +

get_model_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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.