Reduce Claude Code token usage by 70-90% using a free local LLM (Ollama). MCP server + Stop hook with codebase indexing, tool output compression, and turn summarization.

{
  "mcpServers": {
    "cctx": {
      "command": "npx",
      "args": [
        "-y",
        "cctx-optimizer"
      ]
    }
  }
}