Skip to main content
Glama
dshakes

distil

by dshakes
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to distil

  • mcp-context-guard

    AMEOBIUS-space
    A
    license
    Not graded
    quality
    C
    maintenance
    Compresses tool outputs, manages token budgets, deduplicates content, and filters by relevance to optimize context window usage for AI agents.
    MIT

Related Servers

  • mcp-compress-proxy

    LT326
    A
    license
    Not graded
    quality
    B
    maintenance
    A task-aware transparent proxy that wraps stdio MCP servers (such as git, filesystem, and terminal) and compresses large tool outputs field-by-field using declarative YAML profiles, passing narrow intent queries through untouched. Discarded data is stored in SQLite and can be losslessly retrieved via an injected tool, either in full, by line range, or by grep, while errors are always preserved and failures fall back to the raw result.
    MIT

  • TokenSkein

    flaviomartil
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides compression, retrieval, and statistics for local context-economy when interacting with GPT/Codex, enabling efficient token usage and exact recovery of compacted content.
    3
    Apache 2.0

  • cangjie

    KovacBro
    A
    license
    Not graded
    quality
    A
    maintenance
    Exposes six tools over stdio that trim noisy command output, maintain capped state cards and rolling notes, and produce fixed-budget working-memory packs with reversible phrase compression, keeping per-turn context cost constant regardless of conversation length.
    MIT

  • densely

    alibaizhanov
    A
    license
    Not graded
    quality
    B
    maintenance
    Lossless context compression for LLMs, packing text into 2x-8x fewer tokens with byte-exact reconstruction. Provides MCP tools to compress files/text and expand exact slices, verified by sha256.
    45 PyPI
    8
    MIT

  • context-diet

    shapachan385
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI coding agents to retrieve the exact original tool-output slices omitted during lossless context compression, via on-demand expansion of hashed references stored in a shared cross-process SQLite vault. Tracks expansion overhead so agents and users can measure true net token savings across debugging sessions.
    MIT

  • mcp-compress

    ShipItAndPray
    A
    license
    A
    quality
    C
    maintenance
    Data compression MCP server with auto-algorithm selection (gzip, brotli, deflate). 7 tools for compress, decompress, analyze, store, retrieve, list, and stats. Achieves 60x compression on docs, 30x on SQL. Lossless round-trip verified. Zero dependencies.
    9
    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

A4.7/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct role: compress stores and returns a digest, expand recovers the original from a handle, and savings reports cumulative ledger totals. There is no functional overlap or realistic confusion between them.

Naming Consistency4/5

All tools share a consistent distil_ prefix and snake_case style. compress and expand are verb-named, while savings is noun-named, which is a minor deviation but still predictable and readable.

Tool Count5/5

Three tools is exactly the right scope for a focused compression and restore utility. Each tool serves a distinct, necessary function without adding unneeded surface area.

Completeness5/5

The server covers the full intended workflow: compress text, expand it back by handle, and report cumulative savings. Automatic TTL expiration handles cleanup, so there are no obvious dead ends or missing operations for the stated domain.

Maintenance

ActivityActive
ResponsivenessResponsive

Resources