Skip to main content
Glama
laya-mcp

laya-mcp

by fuleinist

Related Servers

Alternatives to laya-mcp

No user-submitted related servers found.

    Related Servers

    • A
      license
      A
      quality
      B
      maintenance
      Provides fast, offline typed decision tools (classify, score, check, triage) to agents via the Model Context Protocol, enabling safe local inference across 100+ languages with calibrated confidence and no text generation.
      8
      21 PyPI
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Exposes four System 1 decision tools — categorical choice, rubric scoring, binary probability assertions, and a pre-execution guardrail — over stdio JSON-RPC. This enables agents to make sub-second routing, triage, and safety decisions without slow generative calls.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to classify plain-language messages against runtime-defined intents, with margin-based doubt flags, beta yes/no checks, and per-intent probability scores, without training examples. It runs self-hosted and supports multilingual intent decisions in about 26 ms per message on a compiled GPU.
      1
      Apache 2.0
    • A
      license
      A
      quality
      A
      maintenance
      Enables agents to make calibrated decisions via six MCP tools for classification, relevance ranking, claim verification, action gating, next-step control, and model listing, using Jev's System One model without generating text.
      6
      25
      MIT

    TDQS

    A3.8/5.0

    Scored across 8 tools

    Disambiguation3/5

    Most tools have distinct purposes, but laya_route and route_step clearly overlap as routing tools, even though the descriptions try to differentiate them. laya_triage and laya_classify could also be confused in some contexts, though the batch-vs-single distinction helps.

    Naming Consistency3/5

    Six tools follow a consistent laya_<verb> pattern, but route_step and verify_step break the convention by dropping the prefix and using verb_noun instead. The names are readable and meaningful, but the mixed style is noticeable.

    Tool Count4/5

    Eight tools is within the ideal range and the set covers the major decision-engine capabilities. The main redundancy is the two routing tools, which slightly weakens the 'every tool earns its place' criterion but does not make the set bloated.

    Completeness4/5

    The tool surface covers the core decision, classification, routing, safety, verification, and health operations well. Minor gaps exist, such as no tool for refitting temperatures or managing the catalog, but these are not blocking for the primary inference and advisory workflows.

    Maintenance

    ActivityMaintained
    ResponsivenessResponsive