tokenfold: Local, provider-neutral compression for LLM prompts, tool schemas, JSON, logs, and diffs

by snchimata · MCP Server · ★ 101

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install tokenfold

pip install tokenfold       # Python 3.9+
npm install tokenfold       # Node.js 22+

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 67/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

clicompressioncontext-windowcost-reductiondeveloper-toolsjsonllmlossless-compressionmcpopenai

Quick Facts

Stars101
Forks25
LanguageRust
CategoryMCP Server
LicenseApache-2.0
Quality Score67/100
Open Issues7
Last Updated2026-11-05
Created2026-07-14
Platformscli, mcp, rust
Est. Tokens~25k

About tokenfold

TOKENFOLD Send less noise. Fit more context. Pay for fewer input tokens. Up to 92% fewer input tokens · lossless by default · exact receipts CLI · Python · TypeScript · Rust · proxy · MCP · local-first · provider-neutral Measured results · Platform · Quick start · Lossy pruning · [Select model](#token

Compatible Skills

These tools work well together with tokenfold for enhanced workflows:

  • tokuin — semantic(0.16)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

tokenfold alternative? Top 6 similar tools

Looking for a tokenfold alternative? If you're comparing tokenfold with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • llmtrim by fkiene · ⭐ 274

    Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted

  • omni by fajarhide · ⭐ 374

    Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twi

  • TokenTamer by borhen68 · ⭐ 129

    A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without los

  • LAP by Lap-Platform · ⭐ 349

    Your agents are guessing at APIs. Give them the actual Agent-Native spec. 1500+ API's Ready To-Use skills, Co

  • tokf by mpecan · ⭐ 200

    Config-driven CLI tool that compresses command output before it reaches an LLM context

  • prompt-caching by flightlesstux · ⭐ 131

    Automatic prompt caching for Claude Code. Cuts token costs by up to 90% on repeated file reads, bug fix sessio

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Rust Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools