# Onde Inference CLI MCP server

> Fine-tune Qwen models with LoRA, export to GGUF, and manage local LLM deployments through a terminal interface or MCP server.

- Repository: https://github.com/ondeinference/onde-cli
- Page: https://hostedmcp.org/servers/ondeinference/onde-cli
- Transport: stdio
- Stars: 5
- License: Apache-2.0
- Latest version: 0.5.1

## Install

### Claude Code

```sh
claude mcp add onde-cli -- npx -y @ondeinference/cli
```

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

```json
{
  "mcpServers": {
    "onde-cli": {
      "command": "npx",
      "args": [
        "-y",
        "@ondeinference/cli"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "onde-cli": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ondeinference/cli"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"onde-cli","type":"stdio","command":"npx","args":["-y","@ondeinference/cli"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "onde-cli": {
      "command": "npx",
      "args": [
        "-y",
        "@ondeinference/cli"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add onde-cli -- npx -y @ondeinference/cli
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.onde-cli]
command = "npx"
args = ["-y", "@ondeinference/cli"]
```

### Gemini CLI

```sh
gemini mcp add -s user onde-cli npx -- -y @ondeinference/cli
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "onde-cli": {
      "command": "npx",
      "args": [
        "-y",
        "@ondeinference/cli"
      ]
    }
  }
}
```

## FAQ

### What can I do with Onde Inference CLI?

You can manage your account, apps, and model catalog, fine-tune Qwen models locally using LoRA, and export them to GGUF format.

### How can I use this with an AI agent?

You can run the tool as an MCP server over stdio to connect it to any MCP-compatible client.

### Does it have a graphical interface?

It features a terminal user interface (TUI) for signing in and managing apps and models.