comfyui-mcp-server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
comfyui-mcp-server
一个 MCP(Model Context Protocol)服务器,让 Agent 通过 MCP 工具直接驱动本地 ComfyUI 实例,专注于 MiniMax H3 视频生成工作流 (文生视频 / 图生视频 / 参考生视频 / 多帧参考)。
它解决什么问题
ComfyUI 的 /prompt 接口只接受 API 格式 的工作流,但我们在 UI 里保存的
工作流是 UI 格式(nodes[] + links[] + definitions.subgraphs,并用 subgraph
封装节点)。本服务器:
列出 / 读取本地 ComfyUI 已保存的 UI 格式工作流
自动把 UI 格式(含 subgraph 封装)展平 成 API 格式
提交任务、轮询进度、下载产物(mp4)
上传参考图(图生视频 / 参考生视频用)
Related MCP server: comfy-h3-mcp
提供的工具
工具 | 说明 |
| 检查 ComfyUI 服务状态(版本、GPU/显存、队列) |
| 列出已保存的工作流 |
| 读取工作流结构摘要(节点类型、提示词节点、可调参数) |
| 生成视频(覆盖 prompt / duration / 比例 / 参考图 / 自定义 overrides) |
| 按 |
| 查看当前运行 / 等待队列 |
| 查询已安装节点类型及其输入参数 |
| 列出本机已安装模型文件 |
安装
npm install依赖:@modelcontextprotocol/sdk、zod。
配置(环境变量)
变量 | 默认值 | 说明 |
|
| ComfyUI 服务地址 |
|
| UI 工作流存放目录 |
|
| 产物下载目录 |
|
| 客户端标识 |
自测
node selftest.mjs会通过 stdio 协议完成握手,并依次调用 comfy_status / comfy_list_workflows /
comfy_get_workflow / comfy_queue_status,最后提交一个 2 秒低分辨率 t2v 任务。
接入(以 Claude Desktop / WorkBuddy 为例)
在 MCP 配置中加入:
{
"mcpServers": {
"comfyui": {
"command": "node",
"args": ["/绝对路径/comfyui-mcp-server/index.js"],
"env": {
"COMFY_HOST": "http://localhost:8188"
}
}
}
}许可证
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
AI video generation MCP server for Kling, MiniMax, Luma & Hunyuan with prompt blueprints.
MCP server for Hailuo (MiniMax) AI video generation
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceDynamically loads ComfyUI workflows as MCP tools, enabling AI assistants to generate images, videos, and audio by executing workflows across categories like text-to-image, image-to-video, and text-to-audio with automatic parameter mapping and progress monitoring.11,925 npm3MIT
- FlicenseAqualityDmaintenanceEnables MiniMax-H3 video+audio generation on a local ComfyUI via five simple tools, including image/reference-to-video, job polling/cancelling, and asset listing, with stateless prompt_id-based job handling.61-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to generate images and videos through natural language by exposing ComfyUI workflows as parameter-configurable MCP tools.10MIT
- FlicenseNot gradedqualityCmaintenanceEnables video generation through ComfyUI workflows, providing tools to list workflows, create and manage video jobs, upload assets, and retrieve results.-