// SCAN REPORT

Cursor Usage

17 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

1 can modify or destroy data

16 read-only

17 tools total

Community server · catalogue entry verified 29/06/2026

How to control Cursor Usage ↓

TOOL MAP

What Cursor Usage exposes to your agents

Read (16) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Cursor Usage tools

Write · High set_spend_limit This tool creates or modifies a spending limit configuration for a user, which is reversible (the limit can be changed or removed later).

1 of Cursor Usage's 17 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Cursor Usage

PolicyLayer is an MCP gateway — it sits between your AI agents and Cursor Usage, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "set_spend_limit": {
    "limits": [
      {
        "counter": "set_spend_limit_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_agent_edits": {
    "limits": [
      {
        "counter": "get_agent_edits_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Cursor Usage — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CURSOR USAGE →

Instant setup, no code required.

FULL CATALOGUE

All 17 Cursor Usage tools

WRITE 1 tools

Write set_spend_limit Set a hard spending limit (in dollars) for a specific team member. Use with caution — this will block the user

READ 16 tools

Read get_agent_edits Get agent edit metrics: suggested vs accepted vs rejected diffs and lines. Shows how effectively the team is u Read get_billing_groups Get billing groups with member lists, group-level spend, and daily spend breakdown. Also returns billing cycle Read get_client_versions Get Cursor client version distribution across the team: which versions are in use and what percentage of users Read get_commands Get command usage analytics: which Cursor commands are being used and how often. Read get_daily_usage Get daily usage data per user: lines added/deleted, applies, accepts, rejects, tabs, requests by mode (compose Read get_dau Get daily active users over time, including breakdowns for CLI, cloud agent, and Bugbot usage. Read get_file_extensions Get top file extensions being edited with AI: which file types get the most AI suggestions, accepts, and rejec Read get_mcp_usage Get MCP (Model Context Protocol) tool usage: which MCP servers and tools are being used, and how often. Read get_model_usage Get model usage breakdown per day: which models are being used, how many messages, and by how many users. Esse Read get_plans Get plan mode adoption: which models are being used in plan mode and how often. Read get_spending Get current billing cycle spending for all team members. Shows spend in dollars, included vs overage, fast pre Read get_tabs Get tab autocomplete usage: suggestions shown vs accepted vs rejected, with line-level detail. Read get_team_members List all team members with their roles and status. Returns name, email, role, and whether they Read get_team_overview Get a comprehensive team overview: member count, total spend, top spenders, DAU, and most-used models. This is Read get_usage_events Get granular per-request usage events with model, token counts, costs, and whether the request was chargeable. Read get_user_deep_dive Deep dive into a specific user

FAQ

Questions about Cursor Usage

How do I prevent bulk modifications through Cursor Usage? +

The Cursor Usage server has 1 write tools including set_spend_limit. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Cursor Usage.

How many tools does the Cursor Usage MCP server expose? +

17 tools across 2 categories: Read, Write. 16 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Cursor Usage? +

Register the Cursor Usage MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Cursor Usage tool call.

Deterministic rules across all 17 Cursor Usage tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CURSOR USAGE →

Instant setup, no code required.

17 Cursor Usage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.