Skip to main content
Glama
fkiene

llmtrim

by fkiene
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Related Servers

Alternatives to llmtrim

No user-submitted related servers found.

    Related Servers

    • tooltrim

      nac7
      A
      license
      A
      quality
      A
      maintenance
      tooltrim reduces the tokens agents spend re-reading bloated tool results. Run it as an MCP server exposing compress and expand_tool_output, or as a gateway in front of any upstream MCP server: it re-exposes the upstream tools unchanged and shrinks each result (HTML/JSON/logs/tables) before it reaches the model, keeping the relevant content only.
      2
      2
      MIT

    • terse

      inth3shadows
      A
      license
      A
      quality
      A
      maintenance
      A transparent proxy that sits in front of any other MCP server and shrinks its tool output before it reaches the model. Lossless by default: the transformed bytes are a denser encoding of the same data, with a round-trip gate asserting an exact inverse over the corpus, so nothing is dropped, summarised, or offloaded to a cache that expires. Repeated calls to the same tool emit a delta against the
      2
      MIT

    • Refract

      LoudiliMed
      A
      license
      A
      quality
      B
      maintenance
      MCP proxy that compresses tool schemas on the fly. Up to 98% token reduction, 100% signal preserved verified after every compression. Zero LLM calls, fully deterministic.
      5
      4
      MIT

    • Headroom Mini

      lea-blum
      F
      license
      B
      quality
      C
      maintenance
      Local MCP server for token optimization, providing tools to compress code/JSON, optimize prompts, and manage placeholder-based content redaction and hydration to reduce LLM token usage.
      5
      -

    • Compendium

      hocestnonsatis
      A
      license
      Not graded
      quality
      A
      maintenance
      MCP server that minimizes LLM token usage by compressing, summarizing, filtering, chunk-referencing, and pruning large context before it reaches the model, with heuristic or local-SLM smart actions, caching, and token counting.
      21 npm
      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

    Disambiguation4/5

    The three tools are mostly distinct: llmtrim_compress targets full request bodies, llmtrim_compress_text targets individual text blobs, and llmtrim_stats reports savings. There is slight overlap between the two compress tools, but their scopes are clearly separated by descriptions.

    Naming Consistency4/5

    All tool names share the llmtrim_ prefix and mostly use a verb_noun pattern (compress, compress_text, stats). The outlier is llmtrim_stats, which uses a noun rather than an action like get_stats, but the overall pattern remains predictable.

    Tool Count5/5

    Three tools is well-scoped for a focused utility server: two compression entry points and one stats/reporting tool. Each tool clearly earns its place and the surface is easy to navigate.

    Completeness4/5

    For the implied domain of LLM request compression, the set covers compressing whole requests, compressing individual text chunks, and retrieving savings reports. Minor gaps like configuration options or batch compression exist, but the core workflow is complete.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources