Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP

Source: Hacker News

Overview

Every MCP server injects its full tool schemas into the context on every turn — 30 tools cost ~3,600 tokens per turn whether the model uses them or not. Over 25 turns with 120 tools, that’s 362,000 tokens just for schemas.

Usage

mcp2cli turns any MCP server or OpenAPI spec into a CLI at runtime. The LLM discovers tools on demand:

mcp2cli --mcp https://mcp.example.com/sse --list             # ~16 tokens/tool
mcp2cli --mcp https://mcp.example.com/sse create-task --help  # ~120 tokens, once
mcp2cli --mcp https://mcp.example.com/sse create-task --title "Fix bug"

Token Savings

Token savings are real, measured with cl100k_base:

• 96 % reduction for 30 tools over 15 turns
• 99 % reduction for 120 tools over 25 turns

Installation

It also ships as an installable skill for AI coding agents (Claude Code, Cursor, Codex):

npx skills add knowsuchagency/mcp2cli --skill mcp2cli

Inspiration

Inspired by Kagan Yilmaz’s CLI vs MCP analysis and CLIHub.

Repository

https://github.com/knowsuchagency/mcp2cli

Discussion

Comments: (Points: 13)