How I Cut MCP Token Usage by 91% (and Learned a Humbling Lesson About Tokenizers)

A developer built mcptoon, a CLI tool that reduces MCP server token usage by 91% by replacing verbose JSON schemas with a compact pipe-delimited format. The tool, which sits between AI coding agents and MCP servers, was verified with tiktoken and is available on GitHub.

When you add MCP servers to your AI coding agent, each one dumps its full JSON schema into context. 255 tools across all servers = 39,964 tokens. On a 128K context window, that's 31% gone before you type a single character. I was literally paying for JSON syntax overhead. Every API call included {"content": {"type":"text","text":"..."} } — 80 tokens to deliver 6 tokens of data. I built a CLI that sits between your agent and MCP servers. It does three things: Instead of full JSON schemas, mcptoon presents tools in a compact pipe-delimited format: Full JSON 287 tokens per tool : {"name":"search","description":"Search the web","inputSchema":{"type":"object","properties":{"q":{"type":"string","description":"Query"},"n":{"type":"number"}},"required": "q" }} SLIM format 26 tokens : search|q:s |n:n 255 tools: 39,964 → 3,511 tokens. 91% saved. Verified with tiktoken.get encoding "cl100k base" . Schemas live on disk in ~/.mcptoon/config.json . Your agent runs mcptoon manifest --slim to see what's available, then mcptoon call <server <tool '{"param":"value"}' --toon to execute. Only the compressed output enters context. Tool results come back as human-readable key-value pairs instead of nested JSON: JSON result 80 tokens : {"content": {"type":"text","text":"{\"name\":\"react\",\"stars\":219000}"} } TOON result 12 tokens : name: react stars: 219000 My first version replaced null with ∅ the empty set symbol . I thought I was being clever. Then someone ran it through tiktoken: null = 1 token, ∅ = 2 tokens. I was literally increasing token count and calling it optimization. The HN community called me out on it. Fair enough — I hadn't measured before shipping. Now everything is tiktoken-verified. true stays true . null stays null . No unicode tricks. At GPT-4o pricing $5/M tokens : pip install mcptoon mcptoon add fetch --stdio npx -y @anthropic/mcp-fetch mcptoon manifest --slim see what's available, compact mcptoon call fetch fetch '{"url":"https://example.com"}' --toon Works with any agent that can run shell commands. One config file for all agents — no more reconfiguring for Claude Code vs Cursor vs OpenCode. 3000 lines of Python, 309 tests, zero dependencies. GitHub: https://github.com/activeing123/mcptoon https://github.com/activeing123/mcptoon What's your biggest MCP token waste? How are others handling this?