DirectoryVllm Mlx MCP
53
Health
fair
61
Popularity
OpenAI and Anthropic 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. Works with Claude Code.
520stars
70forks
Python
Updated March 11, 2026
#anthropic#apple-silicon#audio-processing#claude-code#computer-vision#image-understanding#inference#llm#machine-learning#macos#mllm#mlx#multimodal-ai#speech-to-text#stt#text-to-speech#tts#video-understanding#vision-language-model#vllm
Add to Claude Desktop
Paste this into your claude_desktop_config.json file:
{
"mcpServers": {
"vllm-mlx-mcp": {
"command": "npx",
"args": [
"-y",
"vllm-mlx"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Installation
npx vllm-mlx
Maintenance Healthfair
Freshness25/40
Issue response15/30
Org backing10/20
Longevity3/10
› Updated this quarter
Server Info
Categorytools
LanguagePython
LicenseN/A
StatusACTIVE
Free tier available
Get Your API Key
Claude API — the AI that powers most MCP use cases. Free tier available.
Get Claude API Key →Submit Your Server
Built an MCP server? Get it listed in front of thousands of developers.
List Your Server Free