Skip to main content
Glama
leighefford

jev-kit

by leighefford
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Related Servers

Alternatives to jev-kit

No user-submitted related servers found.

    Related Servers

    • JevMCP

      NicolasRisso
      A
      license
      A
      quality
      B
      maintenance
      Enables 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.
      1
      MIT

    • mcp_jev

      pedroknigge
      A
      license
      A
      quality
      B
      maintenance
      Runs TypeSafe Jev System One packs locally, enabling agents to perform typed Choice, Noul, and Score judgments for tasks like PR auditing, intent routing, and locale classification.
      5
      1
      MIT

    • jev-bridge

      lhviet
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables Claude Code or any MCP client to ask TypeSafe's Jev for calibrated, typed judgments (probabilities, choices, scores) instead of prose, with local caching and cost tracking.
      1
      MIT

    • jev-mcp

      rajasekharponakala
      A
      license
      B
      quality
      C
      maintenance
      Enables 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.
      5
      2
      AGPL 3.0

    • jev-mcp

      emlama
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to save, document, and re-run TypeSafe Jev judgment queries as reusable named tools with OAuth authentication and run logging.
      MIT
    Deploy Server
    Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools target clearly distinct tasks: comedy testing (laugh_track), goal alignment (steer_check), git bisection (semantic_bisect), pairwise physics (physics_interact/physics_sandbox), idea collision (collision_engine), and generic typed evaluation (jev_ask). The physics pair/sandbox tools share a domain but differ in single-pair versus 2-8 item batch usage, and jev_ask is explicitly low-level, so boundaries are mostly clear.

    Naming Consistency4/5

    All names use lowercase snake_case and are readable, with no camelCase or case inconsistency. However the semantic pattern varies (noun_noun, noun_verb, adjective_verb, prefix_verb), so it is not a strict verb_noun convention, but it remains predictable enough.

    Tool Count5/5

    Seven tools is within the well-scoped 3-15 range and each covers a distinct capability: specialized evaluators plus one low-level primitive. No obvious redundant filler.

    Completeness4/5

    The low-level jev_ask primitive allows arbitrary typed evaluations to fill many gaps, while the specialized tools cover audience reaction, goal checking, bisection, physics, and idea collisions. No major lifecycle operation is obviously missing for this judgment/evaluation toolkit, though more domain-specific evaluators could be added later.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources