# Cursor CLI Guide

Cursor’s agent in the terminal, with interactive work and scripted execution.

Canonical URL: https://aiidelist.com/blog/traeide-cursor-cli

Language: en

Published: 2026-10-03

Updated: 2026-10-03

> Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed.

Cursor’s agent in the terminal, with interactive work and scripted execution.

Coding agent · Cursor · macOS · Windows · Linux

 

## Suitable workflows

Cursor users who also work over SSH, in terminal editors or in automation.

## Limitations and billing

The CLI is a separate working surface from the editor; account limits still apply.

## Capabilities we verified

Agent workflow · CLI surface

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

## Pricing & usage

**See official pricing**

Cursor subscription and usage allowance. The cost of metered usage or an external agent can be separate from the subscription.

## Models & access

Model access follows your Cursor account and the CLI’s current model selector.

<span id="cli-setup"></span>

## Install and start the CLI

Use the shell installer on macOS/Linux/WSL, or the documented PowerShell installer on Windows.

```
curl https://cursor.com/install -fsS | bash
```

Open your project folder in a terminal, then run:

```
agent
```

## Account and authentication

Start agent and complete Cursor account authentication.

## Project configuration and tools

Choose Agent, Plan or Ask mode for the task; inspect approvals before enabling unattended changes.

## First task to try

Use a planning conversation to outline a change before applying it to the repository.

## Related CLI tools

[All AI CLI tools →](/blog/traeide-coding-agents)

[Cursor](/blog/traeide-cursor) — AI code editor with agents, project rules and MCP.

[GitHub Copilot CLI](/blog/traeide-copilot-cli) — GitHub’s terminal coding agent with repository context and Copilot account access.

[Codex](/blog/traeide-codex) — OpenAI’s coding agent for local projects and cloud tasks.

## Project evaluation checklist

1. Open a small, familiar project and confirm that your essential language tooling works.
2. Give the agent one bounded change with an observable acceptance criterion.
3. Review the diff, run the project’s checks and compare the result with your current workflow.
4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.

## Related TRAE guides

- [TRAE product overview](/ide/trae)
- [Trae IDE / TraeCode Download](/blog/traeide-download)
- [TraeCode Guide](/blog/traeide-traecode)
- [TraeWork Guide](/blog/traeide-traework)
- [TRAE Pricing: TraeCode & TraeWork](/blog/traeide-pricing)
- [TRAE Models & Model Access](/blog/traeide-models)
- [TraeWork vs TraeCode (Trae IDE)](/blog/traeide-traework-vs-traecode)
- [Trae MCP Setup & Troubleshooting](/blog/traeide-mcp)