token-optimizer-mcp

active

91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository: github.com/ooples/token-optimizer-mcp
Package: npm: token-optimizer-mcp
Run (stdio): npx -y token-optimizer-mcp
The usual command for this package registry; check the repository README for required settings.
License: MIT
Last update: 2026-11-15
GitHub stars: ★ 581
Homepage: www.npmjs.com/package/@ooples/token-optimizer-mcp

ai ai-agents caching claude claude-code codex compression context-engineering cost-optimization developer-tools gemini-cli-extension github-copilot

Listed in

github · source

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.