token-optimizer-mcp
by ooples
Token Optimizer MCP is a Model Context Protocol server that compresses and caches the context sent to AI coding agents, and records how many tokens each agent saves. It is meant to lower the cost of using tools such as Claude Code and Gemini CLI.
- Stars
- 563
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Moderate
- Language
- JavaScript
- Age
- 383 days
What you can do with it
- Compress large tool outputs, logs and search results before they reach your AI coding agent
- Measure token savings per agent in one local ledger
- Share a live local knowledge graph across several command-line AI clients
Make money with it
A freelance developer could set up and tune token-saving configurations for small teams as a paid service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Cut the monthly API or subscription cost of AI coding agents used by a small development team
- Let a freelance developer fit longer coding sessions into the same token budget, so more client work gets done per session
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
It is published as an npm package (@ooples/token-optimizer-mcp) that needs Node.js and must be registered with each AI client as an MCP server.
Follow the official instructions in the project README.
Things to check
- The README's benchmark figures are the author's own and compare against an unnamed alternative, so treat them with caution
- Only useful if you already use supported AI coding agents, which may need paid accounts or API keys
Who's talking about it
Checked 29 Oct 2026. Summary drafted by AI from the project's README.
