Skip to main content
Glama
st412m

cheap-eyes

by st412m
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Related Servers

Alternatives to cheap-eyes

No user-submitted related servers found.

    Related Servers

    • readscout

      Anarchiejs
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables coding agents to delegate the reading of large files, folders, and long logs to local models, returning short answers whose every claim is backed by a quote verified word for word in the source with its real file:line. Everything runs on the user's own hardware, so no file content ever leaves the machine.
      MIT

    • decisions-mcp

      GorOhanyan
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables any AI coding agent to search huge codebases cheaply by sending symptom-based locate, classify, and typed decision questions to OpenRouter decision models, which return ranked file:line locations, confidence scores, and the relevant code instead of the whole repository. It supports model selection, context-aware chunking, and fallbacks so agents can pinpoint bugs or filter files for a fraction of a cent.
      1
      MIT

    • Consult7

      szeider
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to analyze large codebases and document collections by consulting large context window models (up to 2M tokens) via OpenRouter when files exceed the current agent's context limits.
      118 PyPI
      296
      MIT

    • jev-delegate

      koosbcom
      A
      license
      A
      quality
      C
      maintenance
      Enables ranking large workspace search results and classifying English text into caller-defined labels using Jev via OpenRouter, with local secret filtering and spend guards.
      2
      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

    A4.1/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: eyes_stats monitors spend/budget, eyes_run launches a reading job, and eyes_result retrieves or cancels it. The descriptions make the workflow boundaries explicit, so an agent can pick the right one without confusion.

    Naming Consistency5/5

    All three tools follow a strict prefix_noun pattern (eyes_stats, eyes_run, eyes_result) in consistent snake_case. The shared 'eyes_' prefix aids grouping while the suffixes stay distinct.

    Tool Count4/5

    Three tools cover the core lifecycle (check budget, run job, fetch/cancel result) with no redundancy and each earning its place. It is on the lean side, but the scope is narrow enough that this is reasonable rather than thin.

    Completeness4/5

    The surface covers the essential flow: budget check, job execution, result retrieval, and cancellation. A way to list or revisit prior jobs/history is absent, which is a minor gap an agent can mostly work around via the run header id.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources