Skip to content
mcp/harbor
LangChain

Local GPU Imagegen for LangChain

io.github.chevalgrand520/local-gpu-imagegen

MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.

client:LangChain transport:stdio runtime:pypi

Install Local GPU Imagegen in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

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

tools = await client.get_tools()

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

Local GPU Imagegen in other clients

Local GPU Imagegen MCP server