Skip to main content
Glama
Sign In
umpirix

umpirix

by caelum0x
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to umpirix

No user-submitted related servers found.

    Related Servers

    • MCP Server for Laya

      ferronicardoso
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients to make typed, single-pass decisions over text—choosing among options, answering yes/no checks, scoring on a defined ordinal scale, or asking multiple questions about the same text—with probabilities returned for each result. It runs the model locally on CPU and supports stdio and Streamable HTTP transports.
      MIT

    • jev-mcp

      walidboulanouar
      A
      license
      Not graded
      quality
      B
      maintenance
      An MCP server that exposes eleven typed decision tools—check, choose, score, judge, route, triage, guard, grep, rank, compact, and ask—so agents can make fast, branchable yes/no, option-pick, score, and filtering decisions on text via TypeSafe's Jev model.
      7 npm
      2
      MIT

    • laya-mcp

      jerepaira
      A
      license
      A
      quality
      C
      maintenance
      Enables local, LLM-free probabilistic decisions (choice, classification, scoring, yes/no) with real probabilities in 100+ languages, as a drop-in replacement for jev-local tools.
      4
      MIT

    • dsh-jev-mcp

      bojansandhaus
      A
      license
      Not graded
      quality
      C
      maintenance
      A dependency-free stdio MCP server that exposes typed Jev decision tools, enabling coding agents to make binary checks, routing choices, scored rubric ratings, and mixed judgments with calibrated probabilities. It validates questions locally and returns structured JSON results for use in agent workflows.
      204 npm
      1
      MIT

    • decision-lite

      cckyros
      A
      license
      A
      quality
      C
      maintenance
      An MCP server that answers typed noul/choice/score questions about a given state with probability distributions and confidence, for routing, escalation, and gating decisions. It runs on pluggable backends (local Needle 3 or Laya models, or any OpenAI-compatible endpoint) and logs every decision so recorded ground truth can be used to track calibration.
      3
      MIT

    • jev-mcp

      drmedia
      A
      license
      A
      quality
      B
      maintenance
      Lets MCP clients ask typed questions — yes/no, choice, or score — about structured state, including images, and receive calibrated probabilities from System One decision models such as TypeSafe Jev and Cloudflare Clef. Supports TypeSafe, OpenRouter, and local providers selectable per request, with input validation and cost reporting.
      6
      242 npm
      MIT
    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    A3.9/5.0

    Scored across 4 tools

    Disambiguation4/5

    The three primitives map cleanly to distinct output types: single-choice classification, ordinal rating, and binary yes/no. The only overlap is decide, which deliberately aggregates the other three; its description makes the batch role clear, though an agent could occasionally reach for it when a single primitive would do.

    Naming Consistency3/5

    All names are short, lowercase single tokens, which is consistent in form. However, the semantics are mixed: choice and score are nouns, decide is a verb, and noul is an opaque coinage that only the description decodes.

    Tool Count5/5

    Four tools is exactly right for a small set of classification primitives, with one tool per output type plus a convenience aggregator. Nothing feels padded or missing.

    Completeness4/5

    Categorical, ordinal, and binary judgments plus a multi-question batch cover the core decision space well. Minor gaps remain: no multi-label classification and no batch operation across multiple texts, but agents can work around these by composing calls.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Resources