ComfyUI Builder

io.github.MIt9由 GitHub 账号 MIt9 发布v2.4.1更新于 Oct 24, 2026

ComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins.

已验证STDIO仅桌面媒体与设计AI 与机器学习

概览

AI 生成的概览

本地 MCP 服务器,让助手构建、校验并运行 ComfyUI 图像生成工作流,管理模型并获取输出。

可以做什么
  • 发现和查看节点,检查兼容性,并基于内置知识库推荐节点
  • 以编程方式搭建工作流:创建、添加节点、连接、校验,并使用模板与宏
  • 通过 WebSocket 流式进度执行工作流,支持批量与链式运行及进度跟踪
  • 查看系统资源(GPU/显存/内存),列出并检查 checkpoint、LoRA、VAE 等各类模型
  • 列出、下载输出文件,查看和清空队列,中断正在运行的任务
  • 列出并重载插件,通过 ComfyUI-Manager 安装自定义节点和模型
适用场景
适合让助手把一句图像描述变成可运行的 ComfyUI 工作流并直接执行,无需手工编辑 JSON。也适合批量或链式生成,以及在搭建大型工作流前确认硬件上限。
运行要求
以 Node.js 18+ 本地进程通过 stdio 运行,通常用绝对路径启动构建后的 dist/mcp-server.js。执行、队列、模型和输出相关工具需要运行中的 ComfyUI 实例,通过 COMFYUI_HOST 配置。安装自定义节点和模型需要 COMFYUI_PATH;COMFYUI_KNOWLEDGE_DIR 可选,用于指定知识目录。
安装前请注意
通过 ComfyUI-Manager 安装自定义节点和模型会改动 ComfyUI 安装,并拉取第三方代码和大文件,安装前应确认内容。执行、清空队列和中断等工具会直接作用于正在运行的 ComfyUI 实例及其任务。COMFYUI_HOST 只应指向自己可控的 ComfyUI 服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 ComfyUI Builder,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

mcp-comfy-ui-builder

Control ComfyUI from Claude or Cursor — 50+ MCP tools for node discovery, dynamic workflow building, real-time WebSocket execution, and model management. No JSON editing required.

[图片]

[CI] [npm] [Docker] [License: MIT]

Tell your AI assistant what image to generate — it builds and runs the ComfyUI workflow for you.
Works with Claude Desktop, Cursor, and any MCP-compatible client.

[Demo]

Publishable to the MCP Registry via server.json and mcpName.

What is this

  • Knowledge base: Seed knowledge/base-nodes.json and node-compatibility.json from bundled data (62 seed nodes; 100–600+ after sync). No external services required for suggest/build.
  • Sync: Custom packs from ComfyUI-Manager; nodes from running ComfyUI via sync-nodes CLI or on MCP startup.
  • MCP server (50+ tools): Node discovery, dynamic workflow builder, 9 templates (txt2img, txt2img_flux, img2img, …), WebSocket real-time execution, batch/chain, model management, plugin system.
  • Real-time execution: Sub-second progress via WebSocket with automatic polling fallback; ~90% less network traffic for batch runs.

Install

bash
npm install mcp-comfy-ui-builder

Or from source: git clone https://github.com/MIt9/mcp-comfy-ui-builder.git && cd mcp-comfy-ui-builder && npm install

Quick start

  1. Build (postbuild fills knowledge from seed)

    bash
    npm run buildnpm run mcp
  2. Use knowledge in code

    ts
    import baseNodes from './knowledge/base-nodes.json' assert { type: 'json' };

Commands

CommandDescription
npm run seedFill knowledge from seed. Use --force to overwrite.
npm run sync-managerUpdate custom packs list from ComfyUI-Manager
npm run sync-nodesSync nodes from running ComfyUI to knowledge base (requires COMFYUI_HOST)
npm testRun tests (vitest)
npm run mcpStart MCP server (after npm run build)

Documentation

Single entry point — task-oriented navigation:

Requirements

  • Node.js 18+

MCP Server (Cursor / Claude)

Server provides 50+ tools across 9 categories:

Core Features

Node Discovery:

  • list_node_types, get_node_info, check_compatibility, suggest_nodes
  • discover_nodes_live, search_nodes, sync_nodes_to_knowledge

Dynamic Workflow Builder:

  • create_workflow, add_node, connect_nodes, validate_workflow
  • Build workflows programmatically without JSON manipulation

Templates & Macros:

  • list_templates, build_workflow — Pre-built templates (txt2img, img2img, inpainting, upscale, LoRA, ControlNet, batch)
  • create_template, apply_template — Parameterized templates
  • list_macros, insert_macro — Reusable sub-workflows

Real-time execution 📡

  • execute_workflow_sync — Execute with WebSocket progress streaming (sub-second updates)
  • execute_workflow_stream — Full event history collection (WebSocket-only)
  • get_execution_progress — Real-time progress with node-level granularity
  • execute_batch — Concurrent execution with 90% reduced network traffic
  • execute_chain — Sequential workflows with data passing

Resources & Model Management:

  • get_system_resources — GPU/VRAM/RAM + recommendations (max resolution, model size, batch size); call first before building workflows to avoid OOM
  • list_models, check_model_exists, get_workflow_models
  • Supports checkpoint, lora, vae, controlnet, upscale, embedding, clip

Outputs & Queue:

  • list_outputs, download_output, download_all_outputs
  • list_queue, interrupt_execution, clear_queue

Plugins:

  • list_plugins, reload_plugins — Data-only plugin system

Install (requires COMFYUI_PATH):

  • install_custom_node, install_model — Install nodes and models via ComfyUI-Manager

WebSocket features

  • <100ms latency for progress updates (vs 1.5s polling)
  • Node-level tracking: See exactly which node is executing with progress percentage
  • Automatic fallback: Gracefully falls back to polling if WebSocket unavailable
  • Shared connection: Single WebSocket for batch/chain execution (90% reduced traffic)

Set COMFYUI_HOST environment variable for execution/model/output tools:

bash
export COMFYUI_HOST="http://localhost:8188"

See doc/MCP-SETUP.md for full tool list and doc/WEBSOCKET-GUIDE.md for real-time features.

Running MCP

From project root, first build the project, then start the server:

bash
npm run buildnpm run mcp

Or without npm: node dist/mcp-server.js. Server works via stdio (stdin/stdout). More details → doc/MCP-SETUP.md.

Connect MCP (Cursor / Claude)

What you need: Node.js 18+, one-time build (npm run build), absolute path to dist/mcp-server.js, restart after config change. If the server fails to start with «spawn node ENOENT», use the full path to node in command (run which node and put that path). See doc/MCP-SETUP.md → Troubleshooting.

Minimal config (knowledge and workflow tools only):

json
{  "mcpServers": {    "comfy-ui-builder": {      "command": "node",      "args": ["/ABSOLUTE/PATH/TO/mcp-comfy-ui-builder/dist/mcp-server.js"]    }  }}

Use full path in command (e.g. "/opt/homebrew/bin/node") if Cursor/IDE reports «spawn node ENOENT».

With ComfyUI execution (execute_workflow, get_execution_status, list_outputs, etc.): add "env": { "COMFYUI_HOST": "http://127.0.0.1:8188" } to the server block. See doc/MCP-SETUP.md for full checklist, optional env vars (COMFYUI_PATH, COMFYUI_KNOWLEDGE_DIR), and troubleshooting.

Publish on GitHub

  1. Create a new repository on GitHub: name mcp-comfy-ui-builder, visibility Public (or Private). Do not initialize with README, .gitignore, or license (project already has them).

  2. Add remote and push:

    bash
    git remote add origin https://github.com/MIt9/mcp-comfy-ui-builder.gitgit branch -M maingit push -u origin main
  3. If you fork this repo, replace MIt9 with your GitHub username in the URLs above.

Cursor: Settings → MCP; Claude Desktop: config file ~/Library/Application Support/Claude/claude_desktop_config.json (macOS). Replace the path with your absolute path to dist/mcp-server.js, then restart the app. Full guide: doc/MCP-SETUP.md.

License

MIT

来源:README.md,提交 72928ad

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v2.4.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分