# xorbitsai/inference | Model Context Protocol (MCP) Server

> Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

- **Stars**: ⭐ 9,486
- **Language**: Python
- **Native MCP Manifest**: Standard NPX Transport

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

```json
{
  "mcpServers": {
    "inference": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-inference"
      ]
    }
  }
}
```

## ⚡ Cursor MCP Configuration (`.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "inference": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-inference"
      ]
    }
  }
}
```

## 🚀 Launch Commands

- **NPX**: `npx -y @modelcontextprotocol/server-inference`
- **Docker**: `docker run -i --rm mcp/inference`