Jev MCP
Related Servers
Alternatives to Jev MCP
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceEnables coding or reasoning agents to request structured judgments from TypeSafe's Jev model at decision points, including choices, scores, claim verification, and code reviews, with probabilities and confidence returned as data.59 npmMIT
- AlicenseAqualityBmaintenanceEnables AI coding agents to offload yes/no, multiple-choice, and scoring questions to TypeSafe's Jev, returning compact confidence-scored answers to save tokens and improve speed.1MIT
- AlicenseBqualityCmaintenanceEnables AI agents to obtain typed judgments from TypeSafe's Jev System One models, including yes/no probabilities, multiple-choice selections with distributions, and rubric-based scores, directly usable in code.52AGPL 3.0
- AlicenseAqualityBmaintenanceEnables coding agents to query files, logs, and search results through TypeSafe Jev's typed, probabilistic answers, so they retrieve only the needed conclusion instead of raw context. Supports classification, scoring, yes/no checks, extraction, page ranking, and injection screening.11467 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables Claude Code agents to perform structured decision-making through TypeSafe Jev, supporting yes/no checks, route selection, scoring, and batched multi-question judgments with confidence values.1-
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to run source-bound evidence checks and bounded batch judgments for classification, extraction, and decision tasks via TypeSafe Jev.103 npmMIT
TDQS
Scored across 7 tools
Each tool targets a distinct stage in a review/diagnosis workflow: change risk, failure triage, attempt comparison, completion checks, context ranking, findings classification, and generic judgment. A few tools share the same cheap-likelihood framing, but their input types and intended uses are clearly differentiated.
All tools follow the consistent jev_ prefix with a verb_noun pattern (assess_risk, triage_failure, compare_attempts, check_completion, rank_context, classify_findings, judge). There is no mixed casing or stylistic drift.
Seven tools is well-scoped for a probabilistic triage suite, with each tool earning its place as a distinct decision-support primitive. The count is neither too thin nor overloaded.
For the stated domain of cheap probabilistic triage, the set covers the major pre-review decision points and even provides a generic judge fallback for arbitrary yes/no propositions. Potential gaps like diagnosing or fixing are intentionally excluded rather than left as dead ends.