Skip to main content
Glama
thedv91

jev-agent-mcp

by thedv91
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Related Servers

Alternatives to jev-agent-mcp

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

    • 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

      chungsubeen0
      A
      license
      A
      quality
      B
      maintenance
      Enables frontier coding agents to delegate routine probabilistic judgments to TypeSafe Jev, providing calibrated triage signals for failures, attempts, completion, context ranking, findings, risk, and generic evidence-grounded questions.
      7
      MIT

    • ai-to-agent-jev-mcp

      draiagent
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables 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
      -

    • 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
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.6/5.0

    Scored across 5 tools

    Disambiguation4/5

    The tools are generally distinct: review_files vs review_changes differ by input type (files vs diff), and judge/rank_candidates/verify_claim have clear use cases. However, review_files and review_changes could be confused by an agent scanning quickly, and judge with a choice question overlaps with rank_candidates for single-dimension ranking.

    Naming Consistency4/5

    All tool names follow a clear verb_noun pattern (review_files, review_changes, verify_claim, rank_candidates, judge). The pattern is consistent, though 'judge' is a single verb without a noun, which is a minor deviation from the otherwise consistent scheme.

    Tool Count5/5

    With 5 tools, the server is tightly scoped around the Jev review workflow: two review modes (files/changes), a verification tool, and two decision-support tools (judge, rank_candidates). Each tool has a distinct role and no redundancy; the count is ideal for this purpose.

    Completeness4/5

    The tool surface covers the core review lifecycle: review current code, review changes, verify claims, and make decisions. A minor gap is the lack of a tool to aggregate or compare multiple review results, but agents can work around that by calling review tools separately.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources