Local GPU Imagegen

Overview

Local GPU Imagegen is a Model Context Protocol (MCP) server: MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads. In practice that means any MCP-compatible AI assistant can call Local GPU Imagegen's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package local-gpu-imagegen (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.9.1, published under the MIT license, with source at ChevalGrand520/local-gpu-imagegen on GitHub.

Local GPU Imagegen is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Local GPU Imagegen for ChevalGrand520, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "local_gpu_imagegen": {
      "command": "uvx",
      "args": [
        "local-gpu-imagegen"
      ]
    }
  }
}