mcptoon MCP Server
activeing123/mcptoon
[](https://agentrank-ai.com/tool/activeing123--mcptoon/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) One zero-dependency CLI for every MCP server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 341KB, pure Python. | 零依赖 CLI：管所有 MCP 工具与技能，工具发现省 99.2% token。
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
activeing123/mcptoon is a Python MCP server licensed under Apache-2.0. One zero-dependency CLI for every MCP server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 341KB, pure Python. | 零依赖 CLI：管所有 MCP 工具与技能，工具发现省 99.2% token。 Topics: cli, mcp, model-context-protocol, mcp-server, llm, claude, claude-code, cursor, python, codex, mcp-client, token-optimization, context-compression, agent-skills, skill-management, windows, windsurf, zero-dependencies, mcp-cli, mcp-tools.
Ranked #861 out of 24846 indexed tools.
In the top 4% of all indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
219 stars → growing community
Last commit 4d ago → actively maintained
12/12 issues closed → responsive maintainer
4 contributors → small team
No dependents → no downstream usage
209 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/activeing123--mcptoon/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/activeing123--mcptoon/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/activeing123--mcptoon" alt="AgentRank"></a> Matched Queries
From the README
<div align="center" markdown="1"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/activeing123/mcptoon/main/docs/assets/lockup-h-split-dark.svg"> </picture> <h3 align="center">Zero-Config Token Optimization & Unified Governance for MCP Tools and Agent Skills</h3> <p align="center"> <b>Install 1,000 skills and 1,000 MCP tools locally — and never worry about context flooding.</b><br> Cuts tool context by ~90% (99.2% on 255 tools) with zero config across <b>103+ desktop and CLI agents</b>. </p> <p align="center"> <a href="https://pypi.org/project/mcptoon/"></a> <a href="https://github.com/activeing123/mcptoon/stargazers"></a> <a href="https://github.com/activeing123/mcptoon/actions"></a> <a href="#contributing"></a> <a href="https://github.com/activeing123/mcptoon"></a> <a href="https://github.com/activeing123/mcptoon/blob/main/LICENSE"></a> </p> <p align="center"> <a href="https://modelcontextprotocol.io"></a>Read full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.