mcptoon: One zero-dependency MCP gateway CLI for every server and agent skill

by activeing123 · MCP Server · ★ 437

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

Featured in: Skill & Agent Management

How to install mcptoon

pip install mcptoon
docker run --rm mcptoon help

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 71/100

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.

🧪 Tested by Agent Skills Hub

One of 14 tools we ran end to end on the same task for our Skill & Agent Management page (2026-10-09).

Result: Installed a skill with a curl | sh script, showing only its source · removes skills cleanly · syncs to Codex · +350 tokens per session for 20 skills

See the run → · See the whole test →

agent-skillsclaudeclaude-codecodexcontext-compressioncontext-windowcursormcpmcp-climcp-client

Quick Facts

Stars437
Forks26
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score71/100
Last Updated2026-11-18
Created2026-07-27
Platformsclaude-code, cli, codex, mcp, python
Est. Tokens~18k

About mcptoon

mcptoon Add 255 MCP tools → 90,804 tokens gone. Add mcptoon → 117 tokens. Keep 100+ MCP servers always configured. Zero context pollution. No loading. No unloading. One CLI for every agent. If this saves you tokens, please star the repo — it helps others discover it. English Request Feature The problem Every MCP-enabled agent loads all tool schemas into your context — before any work starts.

Compatible Skills

These tools work well together with mcptoon for enhanced workflows:

  • promptguard — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • tokentab — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • single-file-wbs — semantic(0.15)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

mcptoon alternative? Top 6 similar tools

Looking for a mcptoon alternative? If you're comparing mcptoon 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.

  • skilldock by wanghuan9 · ⭐ 611

    SkillDock is an AI skill manager and skill management desktop app for Claude Code, Cursor, Codex, Windsurf, Ge

  • skill-manager by wanghuan9 · ⭐ 265

    SkillDock is a skill manager and MCP manager for installing, viewing, updating, and syncing AI skills and MCP

  • entroly by juyterman1000 · ⭐ 488

    Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an

  • mcp-linker by milisp · ⭐ 345

    Manage MCP servers, skills and plugins across Claude Code, Codex, Cursor and more. Built-in marketplace, one-c

  • mcp by taskade · ⭐ 170

    🤖 Official Taskade MCP server and agent plugin. Connect Claude, Cursor, Codex and other MCP clients to your T

  • 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

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python 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