# MCP

> MCP is an MCP server. Fine-tune a small model on your data and benchmark it against your LLM API, in your AWS account. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **MCP Registry name:** com.synqtune/mcp
- **Listing updated:** 2026-11-13

## About

Fine-tune a small model on your data and benchmark it against your LLM API, in your AWS account.

## Install

### Claude Code (Terminal)

```sh
claude mcp add mcp --env SYNQTUNE_API_TOKEN='<SYNQTUNE_API_TOKEN>' -- uvx synqtune-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ],
      "env": {
        "SYNQTUNE_API_TOKEN": "<SYNQTUNE_API_TOKEN>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ],
      "env": {
        "SYNQTUNE_API_TOKEN": "<SYNQTUNE_API_TOKEN>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ],
      "env": {
        "SYNQTUNE_API_TOKEN": "<SYNQTUNE_API_TOKEN>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ],
      "env": {
        "SYNQTUNE_API_TOKEN": "<SYNQTUNE_API_TOKEN>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp": {
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ],
      "env": {
        "SYNQTUNE_API_TOKEN": "<SYNQTUNE_API_TOKEN>"
      }
    }
  }
}
```

## FAQ

### How do I add MCP to Claude Code?

Run this command in your terminal: claude mcp add mcp --env SYNQTUNE_API_TOKEN='<SYNQTUNE_API_TOKEN>' -- uvx synqtune-mcp

---
Source: https://ai-powered.com/mcp/mcp-mwenhaf7
