Automated README summary
Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An MCP server exposing fifteen judgment tools (verify, gate, classify, rerank, and more) that let coding agents ask TypeSafe's Jev model enumerable questions about evidence and get calibrated probabilities back.
How it uses Jev
The agent passes evidence plus a question with a fixed set of answers; Jev returns probabilities, which policy maps to auto, review, or escalate. The agent uses that action to proceed, double-check, or stop.
Primitives:choicescore
Technique worth stealing
Turn model probabilities into a three-way policy (auto/review/escalate) so confident answers proceed and uncertain ones route to review instead of through.
Try it
Run `uvx --from 'jev-judge-mcp[typesafe]' jev-judge-mcp setup`, then `install`, then `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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.87
- Shows a System One patternFound in material0.91
- Describes handling uncertaintyFound in material0.77
- Reports measured numbersFound in material0.90
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.75 / 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 20 Oct 2026.