vllm mlx
pipStandardOpenAI-compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s.
426210Updated Today
Overview
OpenAI-compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s.
Installation
1Install the package
pip
pip install vllm-mlx2Add to Claude
Add this configuration to your claude_desktop_config.json:
claude_desktop_config.json
{
"mcpServers": {
"waybarrios-vllm-mlx-github": {
"command": "uvx",
"args": [
"pip install vllm-mlx"
]
}
}
}3Verify installation
Restart Claude Desktop, then ask:
"What tools do you have available from vllm mlx?"
Prerequisites
- Python 3.10 or higher
- pip or uv package manager
- Claude Desktop or Claude API access
Configuration
No configuration required. This server works out of the box.
Usage Examples
List Resources
"What resources are available in vllm mlx?"
Claude will query available resources and return a list of what you can access.
Get Details
"Show me details about [specific item] in vllm mlx"
Claude will fetch and display detailed information about the requested item.
Create New
"Create a new [item] in vllm mlx with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
Works with vllm mlx
Related skills
Browse all skillsNeed help with MCP integration?
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.