A Claude Code plug-in that compresses the descriptions of tools supplied by MCP servers. MCP is a standard way for an AI assistant to connect to external tools and services.

Use it when a Claude Code session has many MCP servers or tools and tool-list size is affecting token use. It installs the mcptoon command-line bridge and connects it to the session.

Large tool descriptions consume the assistant's context space before it does any work. This plug-in reduces that discovery information while keeping the tools available through a bridge.

mcptoon — Plugin for Claude Code by activeing123

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/activeing123/mcptoon

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/activeing123/mcptoon/claude-code-plugin/github.svg)](https://agentmods.dev/plugins/activeing123/mcptoon/claude-code-plugin)

Your own site

<a href="https://agentmods.dev/plugins/activeing123/mcptoon/claude-code-plugin"><img src="https://agentmods.dev/badge/plugins/activeing123/mcptoon/claude-code-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/activeing123/mcptoon/claude-code-plugin"><img src="https://agentmods.dev/badge/plugins/activeing123/mcptoon/claude-code-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 1 command, 1 hook, 1 MCP server cost 542 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

mcptoon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude-code-plugin/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "mcptoon",
  "version": "0.8.34",
  "description": "MCP tool-catalog compression for Claude Code. Compresses the tool discovery payload from 71,929 to 581 tokens (-99.2%). Auto-installs the zero-dependency mcptoon CLI (/mcptoon-setup), wires the serve bridge, and teaches the agent when to compress. MCP 2026-07-28 stateless-first bridge included.",
  "author": {
    "name": "activeing123"
  },
  "homepage": "https://github.com/activeing123/mcptoon"
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 1 command, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 542 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago Changed 762c027e2362
8d ago Changed 23f3438047ab
9d ago Changed 8cc4d9c7ff7a
10d ago Changed 784b66c2b5c2
12d ago Changed 2b78c0aa4d17
14d ago Changed 5d3ae709d18c
15d ago Changed e88ae9760e07
16d ago Changed · +1 lines d4c648fce08a
1mo ago First seen · 9 lines scan A 5b515189bc8d

Subscribe to this mod's changes

mcptoon is a plugin published in the GitHub repository activeing123/mcptoon (422 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.

Building agents Claude Code claude codex cursor mcp mcp-client

mcptoon next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcptoonactiveing123/mcptoon	Plugin	422	3d ago	Apache-2.0	A	—	Claude Code
solana-mcp-vybevybenetwork/solana-mcp-vybe	Plugin	2.5k	10d ago	none	A	—	Claude Code
before-you-buildwshobson/agents	Plugin	42k	yesterday	MIT	A	—	Claude Code
mc-agent-toolkitmonte-carlo-data/mc-agent-toolkit	Plugin	93	2d ago	Apache-2.0	A	—	Cursor
mosaic-bridgeMosaicXR-AI/mosaic-bridge	Plugin	11	3d ago	none	A	—	Claude Code
kagekage-core/Kage	Plugin	41	2mo ago	GPL-3.0	A	—	Claude Code
collateMidnightDarling/collate	Plugin	8	5mo ago	Apache-2.0	A	—	Claude Code