Decisions Judge MCP — AI skill for Claude Code
Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request.
How to install Decisions Judge MCP
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open clouatre-labs/decisions-judge-mcp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Decisions Judge MCP does
Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request. Backed by the TypeSafe System One model.
Alternatives in AI
- Fast Agent — Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support 3.7k ★
- Cwc Long Running Agents — Claude Code's built-in /goal command gives you a generator/evaluator loop out of the box: set a completion con 668 ★
- Create Module — Scaffold a fully-typed module with controller, service, router, schema, and model files 325 ★
README
decisions-judge-mcp
[](https://github.com/clouatre-labs/decisions-judge-mcp/actions/workflows/ci.yml) [](https://www.npmjs.com/package/decisions-judge-mcp) [](https://api.reuse.software/info/github.com/clouatre-labs/decisions-judge-mcp)
**Typed decisions for AI agents, as an MCP tool.** Ask yes/no probability (`noul`), choice among options, or score on ordered levels about any JSON application state — all questions answered in one fast request.
Backed by the [TypeSafe System One](https://typesafe.ai) model (Jev) via [`@typesafe-ai/sdk`](https://www.npmjs.com/package/@typesafe-ai/sdk), with an opt-in [Cloudflare Workers AI](https://developers.cloudflare.com/ai/models/typesafe/jev/) provider — see [Providers](#providers).
Get started
Add to `claude_desktop_config.json` (`~/Library/Application Support/Claude/`) — the same JSON shape works for codex, goose, and pi:
{
"mcpServers": {
"decisions-judge": {
"command": "npx",
"args": ["-y", "decisions-judge-mcp"],
"env": { "TYPESAFE_API_KEY": "your-key-here" }
}
}
}
Then ask your agent anything answerable with a judgment — it can call the `judge` tool.
Remote transport (opt-in)
By default the server speaks stdio. Set `JUDGE_TRANSPORT=http` to serve the MCP Streamable HTTP transport (spec revision 2026-07-28) at `POST /mcp` instead:
JUDGE_TRANSPORT=http HTTP_HOST=127.0.0.1 HTTP_PORT=8080 npx -y decisions-judge-mcp
JUDGE_TRANSPORT:stdio(default) orhttp. Any other value exits with an error.HTTP_HOST: bind address, default127.0.0.1.HTTP_PORT: port, default8080; must be 1-65535.
Serving is stateless: each request is handled independently, with no protocol-level sessions (`GET`/`DEL
Related Skills
Jev Curate
High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, f
Jev MCP
TypeSafe AI Jev MCP server for bounded probabilistic decisions: four read-only stdio tools for choices, routin
Reflex Cu
Computer-use MCP server for coding agents: local macOS, local Windows, or remote Windows over SSH, with a fast
Agent Arena
Open-source evaluation framework for LLM agents. Run head-to-head A/B tests, score with LLM-as-judge rubrics,
Typesafe MCP
An mcp connector to evaluate anything fast and cheap. Give your AI agent direct access to typesafe ai's jev mo
Jev Search Rerank Eval
Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over
Related Agents
Jev Judge
Reusable Judge/Verifier question-drafter for text-shaped deliverables — pass/fail, meets-bar yes/no, or rubric
Typesafe Architect
Finds the shape of a TypeSafe solution: decides whether Jev fits at all, what stays in deterministic code, wha
Jill Decider
Answers typed decision questions (choice, score, noul) about a given STATE with calibrated confidence. Used by