What are the requirements to run Hh Mcp Comfyui?
You need Python 3.12+ and a running local ComfyUI instance at `http://127.0.0.1:8188`.
@zjf2671
基本信息
基于Model Context Protocol (MCP)的ComfyUI图像生成服务,通过API调用本地ComfyUI实例工作流生成图片,实现自然语言生图自由
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"hh-mcp-comfyui": {
"command": "uvx",
"args": [
"hh-mcp-comfyui"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Hh Mcp Comfyui is a ComfyUI image generation service built on the Model Context Protocol (MCP). It generates images by calling a local ComfyUI instance via API, enabling natural language image generation through MCP-compatible clients.
Install the package via uvx hh-mcp-comfyui or pip install hh_mcp_comfyui && python -m hh_mcp_comfyui. Ensure a local ComfyUI instance is running at http://127.0.0.1:8188, then configure client tools (Cherry Studio, Cline, Cursor) with the provided MCP JSON configuration.
workflows directoryYou need Python 3.12+ and a running local ComfyUI instance at `http://127.0.0.1:8188`.
The default workflow is `t2image_bizyair_flux`, and the default image size is 1024x1024.
Place exported API-format JSON workflow files into the `workflows` directory under the installation path, then restart the MCP service.
Download sample workflows from the provided GitHub link, copy them into the `workflows` directory of your installation location, then restart the MCP service.
Yes, if using the sample workflows from this project, you must install a specific ComfyUI plugin. See the linked tutorial for installation instructions.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Painless E2E Automation for Mobile and Web

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
Hindsight: Agent Memory That Learns
评论