Skip to content

MTG Judgebot

Rules questions answered like a judge. Every claim cites the Comprehensive Rules, an official ruling or the card's Oracle text, and the citation is checked before you see it.

Never guesses

Nicknames like “bob” and “goyf” resolve through a typed ladder. An ambiguous name becomes a “did you mean…?” prompt, never a guess.

Citations are validated

A quote has to appear verbatim in the rule, ruling or Oracle text it names. A citation that fails is rejected and the model is asked again. An answer with no citation never ships.

Spend is capped

Every model call is metered against a per-process cap that reserves the worst case before sending. The anonymous web page is rate limited per IP on top.

Models are configuration

Anthropic direct, through a proxy, on AWS or Vertex, or any OpenAI-compatible server including a local Ollama. All of it is set in judge.toml, with no code changes.

The community that uses a judgebot runs it, so the spend cap, the judge role and the Discord application are yours. Nothing in the pipeline depends on Discord, so the web page and the command line work before you have a bot token. Read what the judge is, or go straight to requirements and first run.