Skip to content
mcp/harbor
LangChain

GPU Server for LangChain

io.github.mesutoezdil/mcp-gpu-server

MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature

client:LangChain transport:stdio runtime:pypi

Install GPU Server in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "mcp-gpu-server": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["mcp-gpu-server"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

GPU Server in other clients

GPU Server MCP server