Automated README summary
Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local stdio MCP server for MCP clients and Codex that exposes a single tool, jev_decide, for typed decisions through any SDK-compatible decision API endpoint configured with BASE_URL and MODEL.
How it uses Jev
Jev answers typed questions (choice, score, noul) over caller-supplied state, returning probabilities, confidence, and token usage. The MCP returns these judgments; the caller owns thresholds, escalation, and action execution. Batch independent questions over the same context in one call, with answers retaining question IDs.
Primitives:choicescorenoul
Technique worth stealing
Batch independent typed questions over one shared context in a single call, keeping question IDs on each answer.
Try it
npx -y jev-decision-mcp@0.3.0 with API_KEY, BASE_URL, and MODEL set.
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 patternnot found in the excerpt0.13
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.03 / 2
- About JevFound in material0.98
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 22 Oct 2026.