get_agent_edits

Get agent edit metrics: suggested vs accepted vs rejected diffs and lines. Shows how effectively the team is using AI-generated code.

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

What get_agent_edits does on Cursor Usage

AI agents call get_agent_edits 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_agent_edits needs a policy

This tool retrieves and queries usage analytics and metrics data. It has no side effects: it does not create, modify, delete, or execute operations. It does not move money or trigger external state changes. The blast radius of misuse is minimal — an agent could retrieve analytics data but cannot harm systems or cause irreversible damage. Classified as Read with low severity.

From the tool's definition Tool name 'get_agent_edits' and description 'Get agent edit metrics' indicate a retrieval operation. The description specifies it shows metrics on 'suggested vs accepted vs rejected diffs and lines' — purely observational analytics data with no modification,…

Questions about get_agent_edits

What does the get_agent_edits tool do? +

Get agent edit metrics: suggested vs accepted vs rejected diffs and lines. Shows how effectively the team is using AI-generated code. 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_agent_edits? +

Register the Cursor Usage MCP server in PolicyLayer and add a rule for get_agent_edits: 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_agent_edits? +

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

Can I rate-limit get_agent_edits? +

Yes. Add a rate_limit block to the get_agent_edits 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_agent_edits completely? +

Set action: deny in the PolicyLayer policy for get_agent_edits. 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_agent_edits? +

get_agent_edits 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.