V
Vllm MCP
A Model Context Protocol (MCP) server that enables text models to call multimodal models. This server supports both OpenAI and Dashscope (Alibaba Cloud) multimodal models, allowing text-only models to process images and other media formats through standardized MCP tools.
Created 10/3/2025
Updated 2 months ago
README
Repository documentation and setup instructions
GitHub API error: 403
Quick Setup
Installation guide for this server
Install Package (if required)
uvx vllm-mcp
Cursor configuration (mcp.json)
{
"mcpServers": {
"stanleychanh-vllm-mcp": {
"command": "uvx",
"args": [
"vllm-mcp"
]
}
}
}
Author Servers
Other servers by StanleyChanH