这是一个基于模型上下文协议(MCP)的ComfyUI图像生成服务,通过API调用本地的ComfyUI实例来生成图像。
在Cherry Studio中的使用
在Cline中的使用
确保已安装Python 3.12+
2. 使用uv管理Python环境:
# 在macOS和Linux上。
$ curl -LsSf https://astral.sh/uv/install.sh | sh
# 在Windows上。
$ powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# 更新uv(非必要操作):
$ uv self update
$ uvx hh-mcp-comfyui
INFO:hh_mcp_comfyui.server:正在扫描工作流程:C:\Users\tianw\AppData\Local\uv\cache\archive-v0\dp4MTo0f1qL0DdYF_BYCL\Lib\site-packages\hh_mcp_comfyui\workflows
INFO:hh_mcp_comfyui.server:启动ComfyUI MCP服务器...
$ pip install hh_mcp_comfyui
$ python -m hh_mcp_comfyui
INFO:hh_mcp_comfyui.server:正在扫描工作流程:F:\Python\Python313\Lib\site-packages\hh_mcp_comfyui\workflows
INFO:hh_mcp_comfyui.server:启动ComfyUI MCP服务器...
以上消息表示服务已成功启动
您必须确保本地的ComfyUI实例正在运行(默认地址:http://127.0.0.1:8188)[ComfyUI安装地址](https://github.com/comfyanonymous/ComfyUI.git)
{
"mcpServers": {
"hh-mcp-comfyui": {
"command": "uvx",
"args": [
"hh-mcp-comfyui@latest"
],
"env": {
"COMFYUI_API_BASE": "http://127.0.0.1:8188",
"COMFYUI_WORKFLOWS_DIR": "/path/hh-mcp-comfyui/workflows"
}
}
}
}
</details>
<details>
<summary>pip MCP服务配置</summary>
您需要先在命令窗口执行以下命令:pip install hh_mcp_comfyui
{
"mcpServers": {
"hh-mcp-comfyui": {
"command": "python",
"args": [
"-m",
"hh_mcp_comfyui"
],
"env": {
"COMFYUI_API_BASE": "http://127.0.0.1:8188",
"COMFYUI_WORKFLOWS_DIR": "/path/hh-mcp-comfyui/workflows"
}
}
}
}
</details>
<details>
<summary>Docker MCP服务配置</summary>
前提条件是已经安装了Docker
{
"mcpServers": {
"hh-mcp-comfyui": {
"command": "docker",
"args": [
"run",
"--net=host",
"-v",
"/path/hh-mcp-comfyui/workflows:/app/workflows",
"-i",
"--rm",
"zjf2671/hh-mcp-comfyui:latest"
],
"env": {
"COMFYUI_API_BASE": "http://127.0.0.1:8188"
}
}
}
}
</details>
---注意使用下面的uvx或pip方法找到您的安装工作流程目录,添加样本工作流程,然后重新启动您的MCP服务
uvx
$ uvx hh-mcp-comfyui
pip
# 首先安装依赖
$ pip install hh_mcp_comfyui
$ python -m hh_mcp_comfyui
使用MCP Inspector测试服务器端工具
$ npx @modelcontextprotocol/inspector uvx hh-mcp-comfyui
$ pip install hh_mcp_comfyui
$ npx @modelcontextprotocol/inspector python -m hh_mcp_comfyui
$ npx @modelcontextprotocol/inspector docker run --net=host -i --rm zjf2671/hh-mcp-comfyui
然后点击图中所示的连接进行调试:
t2image_bizyair_flux/path/hh-mcp-comfyui/workflows中将工作流程JSON文件放置在/path/hh-mcp-comfyui/workflows目录中
如果是使用uvx和pip启动方法,请参考上面的将样本工作流程复制到指定的工作流程目录部分
重启服务以自动加载新的工作流程
.
├── .gitignore
├── .python-version
├── pyproject.toml
├── README.md
├── uv.lock
├── example/ # 示例工作流目录
│ └── workflows/
│ ├── i2image_bizyair_sdxl.json
│ ├── t2image_bizyair_flux.json
│ ├── i2image_cogview4.json
│ └── t2image_sd1.5.json
├── src/ # 源代码目录
│ └── hh_mcp_comfyui/
│ ├── comfyui_client.py # ComfyUI客户端实现
│ ├── server.py # MCP服务主文件
│ └── workflows/ # 工作流文件目录
# 克隆仓库。
$ git clone https://github.com/zjf2671/hh-mcp-comfyui.git
$ cd hh-mcp-comfyui
# 初始化虚拟环境。
$ uv venv
# 激活虚拟环境。
$ .venv\Scripts\activate
# 安装依赖。
$ uv lock
Resolved 30 packages in 1ms
# 同步依赖。
$ uv sync
Resolved 30 packages in 2.54s
Audited 29 package in 0.02ms
$ uv --directory 你本地安装目录/hh-mcp-comfyui run hh-mcp-comfyui
INFO:__main__:正在扫描工作流程:D:\cygitproject\hh-mcp-comfyui\src\hh_mcp_comfyui\workflows
INFO:__main__:注册资源:workflow://t2image_bizyair_flux -> t2image_bizyair_flux.json
INFO:__main__:启动ComfyUI MCP服务器...
$ npx @modelcontextprotocol/inspector uv --directory 你本地安装目录/hh-mcp-comfyui run hh-mcp-comfyui
{
"mcpServers": {
"hh-mcp-comfyui": {
"command": "uv",
"args": [
"--directory",
"项目绝对路径(例如:D:/hh-mcp-comfyui)",
"run",
"hh-mcp-comfyui"
],
"env": {
"COMFYUI_API_BASE": "http://127.0.0.1:8188",
"COMFYUI_WORKFLOWS_DIR": "/path/hh-mcp-comfyui/workflows"
}
}
}
}
git checkout -b feature/AmazingFeature)git commit -m 'Add some AmazingFeature')git push origin feature/AmazingFeature)<center></center>