Prerequisites
Before setting up the integration, ensure you have:- Unbound CLI: Installed and logged in — see the CLI guide
- Cursor: Download Cursor
Setup with Unbound CLI
✅ Cursor restarted. If it cannot relaunch Cursor it prints Restart Cursor instead, and you restart it yourself.
A Warn policy does not stop the call on Cursor: the command runs under Cursor’s normal flow, and the warning is recorded and passed to the agent as context. Use Block to stop it, or Require Slack Approval to put a person in the loop — the first attempt is denied with a message telling the developer to approve in Slack, and the agent’s retry waits for the answer.
Usage
Basic Usage
After setup, Cursor’s own actions are checked against your policies before they run. The hooks cover twelve points in Cursor’s workflow:
Matching actions are blocked, audited or sent for Slack approval inline, before the action runs.
Security Benefits
Using Cursor with Unbound Security AI Gateway provides:- Request Monitoring: Every prompt, shell command, file read, file edit and MCP call is logged
- Analytics: See which files are most touched by AI through coding agents
- Compliance: Ensure AI interactions meet your organization’s standards
- Audit Trail: Complete visibility into AI usage patterns
Unbound CLI
Install the CLI to set up and manage tools
Tool Policies
Configure security guardrails for AI tools

