Semantic package + memory store — the more your AI Agent uses it, the better it understands your MaxCompute.
Install mcs for me, read this guide fully then follow step by step: curl -fsSL https://raw.githubusercontent.com/aliyun/maxcompute-semantic/main/scripts/install.md
Three nouns. Every command revolves around them.
You configure a profile → mcs produces a semantic package → agent reads it to write SQL
scenario = [A] + [B] + accumulated annotate / memory
The agent invokes mcs via a skill using natural language; you can also open a terminal and run mcs commands directly.
Give your AI Agent a colleague who knows MaxCompute.
A single mcs skill install --all symlinks SKILL.md into Claude Code / Cursor / Codex / Gemini / Qwen / OpenCode and 50+ more platforms. All agents auto-sync when mcs upgrades.
mcs build scans and indexes tables / columns / JOINs / UDFs / annotations in one pass. The agent reads the result before generating SQL.
Generates SQL in MaxCompute dialect. mcs sql cost gates execution against a configurable threshold before running.
mcs memory accumulates query experience. Similar questions are recalled via inverted-index + vector hybrid retrieval — accuracy improves with use.
Install with one command. New versions are auto-detected and prompted. mcs update upgrades in place.
Covers config / auth / network / skill checks. -f json output lets agents parse results automatically.
What to do after installation. Every command has full --help examples.
Tell your agent "install mcs for me" — it follows install.md to set up the CLI and skill. Then ask any MaxCompute data question; the skill guides you through auth and query execution.
See what each version adds, changes, and fixes. The changelog is synced automatically by the release pipeline.
release notes →In your AI agent, say "report an mcs bug" — the skill walks through the full issue-filing workflow.