Automated README summary
Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local stdio MCP server that exposes TypeSafe Jev judgments to MCP clients such as Cursor and Codex. It routes coding-loop steps, selects prepared tool calls, reviews patches, verifies claims, screens untrusted content, ranks candidates, checks scope, triages failures, and assesses risk; the host agent still edits files and runs commands.
How it uses Jev
Each tool sends a state plus typed questions to Jev and returns Choice, Score, or Noul answers with token usage and an action of auto, review, or escalate. Host code prepares exact tool calls; Jev selects among them and returns an executable call only for a confident, validated selection. Jev never invents arguments or executes tools.
Primitives:choicescorenoul
Technique worth stealing
Fuse routing and prepared-call selection into one Jev request so the host spends one model turn instead of two.
Try it
npm ci && npm run build, set TYPESAFE_API_KEY, then run node dist/index.js doctor.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.96
- Shows a System One patternunclear0.60
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.47 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 24 Oct 2026.