AI Token Optimizer

An MCP server that cuts AI coding-agent token usage by 60–80% via framework-aware context optimization.

AI coding agents read whole files when they need 15 lines. They load *.g.dart, R.java, node_modules/, and dist/ into context — then do it again next turn. AI Token Optimizer is a Model Context Protocol server that intercepts those tool calls and strips framework noise before it reaches the model.

Works with anything that speaks MCP: Claude Code, Cursor, Cline, Continue, Zed, JetBrains AI, GitHub Copilot agent mode, Antigravity, Windsurf, OpenAI Codex CLI.

Quickstart

npm install -g @ai-optimizer/core

Then point your agent at the ai-optimizer stdio server. For Claude Code, add to ~/.claude/settings.json:

{
  "mcpServers": {
    "ai-optimizer": {
      "command": "ai-optimizer"
    }
  }
}

Or scaffold the config and preview your savings automatically:

npx @ai-optimizer/init
# "we'd skip 47 files, ~14K tokens/session, ~$0.42/session at Sonnet pricing"

Full per-agent setup (Cursor, others), LSP install, and verification steps live in packages/core/README.md.

Related MCP server: parecode

What it does

It registers tools the agent uses instead of its built-in file/dir/error reads:

When a project type is detected (e.g. Python via pyproject.toml), the matching pack's ignore rules activate automatically. .gitignore is respected on top.

Tiers

See PRICING.md. Behavior-changing or data-sharing features (scheduler, work-stealing, telemetry) are off by default and require explicit opt-in. Display-only features (dollar-value savings) default on.

Monorepo layout

Architecture details: ARCHITECTURE.md.

Development

npm install            # at repo root (workspaces)
npm run build          # build all packages
npm test               # run all test suites

Security

Local-only by design — license validation is the only network call. Report vulnerabilities per SECURITY.md.

License

Core engine is MIT — see LICENSE. Pro/Team packs are proprietary.