Sazabi
Sandbox CLIs

Cursor

Give the Sazabi agent the Cursor CLI (cursor-agent) in its sandbox to run headless AI agent sessions.

About

This CLI connection makes the Cursor CLI (cursor-agent) available in the Sazabi agent's sandbox. The agent can use it for headless AI agent runs. The tool is baked into the sandbox image; connecting it authenticates the already-installed CLI.

Prerequisites

  • A Sazabi project.
  • A Cursor API key (CURSOR_API_KEY), available from your Cursor account settings.

Set up in the dashboard

Configure the sandbox in the dashboard under Settings > Sandbox CLIs.

Find Cursor in the catalog

In Settings > Sandbox CLIs, find Cursor under Browse sandbox CLIs and choose to connect it.

Provide credentials

Enter the required value: CURSOR_API_KEY — the API key for your Cursor account. Save to store it securely; Sazabi injects it into the sandbox when the agent runs.

Set up with the CLI

You can also configure the Cursor CLI connection with the Sazabi CLI (installed and authenticated — see CLI reference).

sazabi sandbox-clis set --type cursor-cli --env CURSOR_API_KEY=<your-cursor-key>

To validate the credentials without saving, run the same command with test in place of set (the test command also requires the --env flags).

Verify

Ask the agent, in a thread, to run the cursor-agent CLI (a read-only or status command) and confirm it returns real output from your account. If the command is not found, the CLI connection may not be enabled; if it runs unauthenticated, recheck the credentials.

Troubleshooting

Command not found — Confirm the Cursor CLI connection is enabled for the project under Settings > Sandbox CLIs.

Authentication fails — Recheck the credential values; a rotated or revoked token must be re-entered under Settings > Sandbox CLIs or with sazabi sandbox-clis set --type cursor-cli.

Further reading