# Cursor CLI — card for AI agents

Cursor's terminal agent (`agent`), which runs Cursor's coding agent interactively or headlessly in the terminal, CI and scripts, with Agent, Plan and Ask modes and handoff to cloud agents. It uses a Cursor account and Cursor plans.

Maker: Cursor · category: Terminal coding agents

## Price
- Cursor now bundles AI and X features together: Free (limited AI usage), Plus $8/month (Grok models, X features), Premium $30/month (4x usage, cloud agents, third-party models), Super $100/month (15x usage, priority access), Ultra $200/month (50x usage, earliest access), Teams $30+/user/month (pooled usage, team management), Enterprise custom. Third-party models billed separately by usage.
- Free tier: yes
- Paid from $8/month with monthly billing
- Pricing page: https://cursor.com/pricing
- Checked: 2026-11-07

## Install
- Homebrew: `brew install --cask cursor-cli`

## Facts
- Interfaces: CLI
- Platforms: macOS, Linux, Windows
- Status page: https://status.cursor.com

## Numbers (AgentGid data)
- Gid Score: 31 (rank #229); limited data: 2/4 score components have public numbers (public popularity and activity, not quality)

## Details (plan limits, live status, safety; from AgentGid's data)
Cursor CLI by Cursor. Category: Terminal coding agents. Type: terminal agent. Cursor's terminal agent (`agent`), which runs Cursor's coding agent interactively or headlessly in the terminal, CI and scripts, with Agent, Plan and Ask modes and handoff to cloud agents. It uses a Cursor account and Cursor plans. Proprietary Pricing (checked 2026-11-07): Cursor now bundles AI and X features together: Free (limited AI usage), Plus $8/month (Grok models, X features), Premium $30/month (4x usage, cloud agents, third-party models), Super $100/month (15x usage, priority access), Ultra $200/month (50x usage, earliest access), Teams $30+/user/month (pooled usage, team management), Enterprise custom. Third-party models billed separately by usage. Free tier: yes. Interfaces: CLI Platforms: macOS, Linux, Windows Models: Models offered through Cursor plans, selectable with the --model flag Supports: mcp, multi_agent, headless Data: Gid Score 31/100, #229 overall; #23 in its category. Live status now: All systems operational. Incidents in the last 30 days: 7 (1 major). Last incident: Elevated errors for OpenAI model requests on 2026-11-09.

## Price history (from archived copies of the official pricing page)
- Archived pricing pages read: 27 months, 2024-06 to 2026-10 (Internet Archive copies of https://cursor.com/pricing)
- Cheapest paid plan: $20/mo in 2024-06, $20/mo in 2026-10; lowest seen $16/mo (2026-06)
- Price changes seen: 5: 2025-07: New plan Ultra at $200/mo; 2025-09: Pro: $20 → $60/mo; 2026-04: New plan Bugbot Pro at $40/mo, New plan Bugbot Teams at $40/mo; 2026-06: Pro: $60 → $48/mo, Ultra: $200 → $160/mo, Teams plan no longer listed; 2026-07: New plan Individual at $20/mo, New plan Teams at $40/mo, Pro plan no longer listed
- Full history with links to each archived copy: https://agentgid.com/pricing/history/cursor-cli/

## Alternatives in the same category
- Claude Code: https://agentgid.com/agents/claude-code/agent.md
- OpenAI Codex: https://agentgid.com/agents/openai-codex/agent.md
- OpenCode: https://agentgid.com/agents/opencode/agent.md
- Pi: https://agentgid.com/agents/pi/agent.md
- Gemini CLI: https://agentgid.com/agents/gemini-cli/agent.md
- Cline: https://agentgid.com/agents/cline/agent.md

## Links
- AgentGid page: https://agentgid.com/agents/cursor-cli/
- Source: https://cursor.com/blog/cli
- Source: https://cursor.com/docs/cli/overview
- Source: https://cursor.com/pricing
- Source: https://cursor.com/cli
- Source: https://formulae.brew.sh/api/cask/cursor-cli.json

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
