DecisionLint: Jev/Luna Lint MCP server

DecisionLint

Lint the questions you send to a decision model: TypeSafe's Jev, OpenAI's Decisions API, and every platform that serves either shape, from OpenRouter and Vercel AI Gateway to a llama.cpp on your own machine. DecisionLint reads them out of your JSON and your code, and reports the ones written in a way that is measured to produce bad answers. Linting makes no API calls and needs no key. One optional command asks the model itself to check a file, using your own key, at whichever platform you send it to.

By the author of the LE tools.

Install

ext install nolindnaidoo.decisionlint.

• VS Code: search for DecisionLint in the Extensions view, or run

nolindnaidoo.decisionlint.

• Cursor, VSCodium and other editors that use Open VSX: the same name,

• Command line: npx decisionlint. Nothing to install first.
• MCP server, for an agent host: npx -y decisionlint-mcp.

At a glance

a finding you disagree with.

• Lints as you type in JSON, JavaScript, TypeScript, Python, Rust and Go.
• Fixes on the lightbulb for the mechanical mistakes, and a way to silence

MCP server. One settings file covers all three.

• The same rules in CI, from a command line, and for AI agents, from an

OpenAI's /v1/decisions shape, predicate, choices and levels, are read into the same rules, and the AI SDK's decide() call for either. The limits a request is held to are the platform's own, read from the model id's spelling, a URL in the file or a target setting: Vercel's 255 choices, LiteLLM's 128 questions, none where a platform publishes none.

• Every platform, one set of rules. TypeSafe's /v1/systemone shape and

whether your questions have problems a text pattern cannot see, and one re-sends a question with its layout changed to see whether the answer holds. Both go to the platform the model id names, or to an endpoint you set, a local llama.cpp included.

• Two optional commands that use your own key: one asks the model

A request like this one looks fine and has three problems:

{
  "model": "jev-latest",
  "state": "My parcel came three days late and the lid is cracked.",
  "questions": {
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this?",
      "criteria": { "billing": "Charges and refunds", "delivery": "Late or damaged parcels" }
    },
    "late": { "type": "noul", "instructions": "Did more than two parcels arrive late?" }
  }
}

What it catches

Jev and Luna guarantee the type of the answer, not the answer. A badly formed question still comes back with a confident-looking number. These rules catch the mistakes that can be read from the text.

Shortened. The full README is on GitHub.