Tuning Engines

Overview

Tuning Engines is a Model Context Protocol server that enables domain-specific LLM fine-tuning, letting you train sovereign models on your own data without infrastructure overhead. It exposes fine-tuning capabilities as tools that AI assistants can invoke directly, making model customization accessible through your favorite MCP client.

The server runs locally via the npm package tuningengines-cli, communicating over stdio on your machine. You'll need to provide the TE_API_KEY environment variable to authenticate. Version v0.3.5 is published under the MIT license, with source code available at cerebrixos-org/tuning-engines-cli on GitHub.

Tuning Engines belongs in the AI & Agents category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this project, claim your listing to verify ownership, earn a Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "tuning_engines": {
      "command": "npx",
      "args": [
        "-y",
        "tuningengines-cli"
      ],
      "env": {
        "TE_API_KEY": "<te-api-key>"
      }
    }
  }
}

Requires TE_API_KEY