
Mmx Cli
A comprehensive CLI wrapper for MiniMax's AI platform that handles text, image, video, speech, and music generation from the terminal. The tool shines in automated workflows with proper agent flags like `--non-interactive` and `--output json` for clean machine-readable responses. Video generation is async by default but can poll until completion, while music generation supports detailed prompts with lyrics, vocals, and genre specifications. The authentication persists locally and region detection is automatic. Worth noting that video tasks require polling or webhooks, and music is limited to 3 RPM on the free tier, but the unified interface across all MiniMax capabilities makes it solid for content automation pipelines.
- skills.sh installs
- 32.5K
- GitHub stars
- 2.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add minimax-ai/cli --skill mmx-cli --agent claude-codeInstalls into .claude/skills of the current project.
Files
MiniMax CLI — Agent Skill Guide
Use mmx to generate text, images, video, speech, transcribe audio, and perform web search via the MiniMax AI platform.
Prerequisites
# Install
npm install -g mmx-cli
# Auth (OAuth persists to ~/.mmx/credentials.json, API key persists to ~/.mmx/config.json)
mmx auth login --api-key sk-xxxxx
# Verify active auth source
mmx auth status
# Or pass per-call
mmx text chat --api-key sk-xxxxx --message "Hello"
Region is auto-detected. Override with --region global or --region cn.
Agent Flags
Always use these flags in non-interactive (agent/CI) contexts:
| Flag | Purpose |
|---|---|
--non-interactive | Fail fast on missing args instead of prompting |
--quiet | Suppress spinners/progress; stdout is pure data |
--output json | Machine-readable JSON output |
--async | Return task ID immediately (video generation) |
--dry-run | Preview the API request without executing |
--yes | Skip confirmation prompts |
Commands
text chat
Sponsors
Details
- Repository
- github.com/minimax-ai/cli
- Categories
- Backend & APIs, CLI & Terminal
- First seen
- Apr 16, 2026