MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
ComfyUI-MCP-Servergithub.com/raphiki/ComfyUI-MCP-Serverupdated this year
A SSE MCP Server to run ComfyUI workflows
MIT ★ 1 -
comfyui-mcp-servergithub.com/joenorton/comfyui-mcp-serverupdated this year
lightweight Python-based MCP (Model Context Protocol) server for local ComfyUI
Apache-2.0 ★ 412 -
Secure MCP server for ComfyUI with workflow inspection and audit logging
pypi MIT License -
comfyui-agentgithub.com/josephoibrahim/comfyui-agentupdated this year
AI co-pilot for ComfyUI — inspect, discover, modify, and execute workflows through natural conversation
pypi MIT -
Portable Windows MCP server for ComfyUI discovery and Civitai model search/downloads. No Python or Node setup. ComfyUI 模型管理桥接。
MIT -
comfyui-mcpgithub.com/shawnrushefsky/comfyui-mcpupdated this year
MCP server for ComfyUI - Enables AI assistants to generate images, video, audio, and 3D
MIT ★ 19 -
خادم MCP للربط مع ComfyUI وتوليد صور FLUX وتحريك الفيديو SVD | A local MCP server bridging LLMs with ComfyUI for FLUX image and SVD video generation.
NOASSERTION -
Status: partial - not auto-wired (-Mcp all skips this package).
NOASSERTION -
@iflow-mcp/artokun-comfyui-mcpgithub.com/artokun/comfyui-mcpupdated this year
MCP server for ComfyUI — workflow execution, visualization, composition, registry, and skill generation
npm MIT -
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
npm MIT ★ 925 -
A Python MCP Server that converts ComfyUI workflows into parameter-configurable tools for AI agents. | 将 ComfyUI 工作流转化为参数可配置的 MCP 工具,供 AI 代理通过自然语言驱动图像与视频生成。
MIT ★ 6 -
@metabrain-labs/comfyui-mcp-servergithub.com/metabrain-labs/comfyui-mcp-server-typescriptupdated this year
MCP Server that transforms ComfyUI workflows into AI-callable tools for Claude, Cursor, Dify and more
npm MIT -
MCP server (HTTP/SSE) for image generation with ComfyUI (SDXL) on your own GPU. Python + FastMCP. Self-hosted, MIT.
MIT ★ 1 -
Secure MCP server for ComfyUI — workflow inspection, path sanitization, rate limiting, and audit logging. Generate images from Claude and other AI assistants with built-in security controls.
MIT ★ 2 -
ComfyUI-MCP-Server-TypeScriptgithub.com/MetaBrain-Labs/ComfyUI-MCP-Server-TypeScriptupdated this year
A TypeScript MCP Server that converts ComfyUI workflows into parameter-configurable tools for AI agents. | 将 ComfyUI 工作流转化为参数可配置的 MCP 工具,供 AI 代理通过自然语言驱动图像与视频生成。
MIT ★ 10 -
comfyui-weavergithub.com/GuusF/comfyui-weaverupdated this year
🧵 Weaves Claude Code into ComfyUI - an MCP bridge that runs your renders (local + Comfy Cloud) without disturbing your work, QCs them by actually looking at them, and ships a script-to-screen film pipeline on top.
MIT ★ 3 -
comfyui-mcp-multiagentgithub.com/neoanthropocene/comfyui-mcp-multiagentupdated this year
Antigravity + Claude Code plugin + MCP server for ComfyUI - 96 tools, 16 AI skills (Flux, WAN, LTX video, Qwen, Civitai), live graph editing from your Claude session. Generate images, video & audio, manage models and custom nodes.
npm MIT -
comfy-ctrlgithub.com/holo-q/comfy-ctrlupdated this year
Remote control bridge for ComfyUI — server extension, Python client, and MCP server
MIT -
Download_Toolsgithub.com/EricRollei/Download_Toolsupdated this year
Comprehensive Download tools for both Comfyui based workflows and MCP servers
NOASSERTION ★ 6 -
Comfy-Cozygithub.com/JosephOIbrahim/Comfy-Cozyupdated this year
AI copilot for ComfyUI. Say “dreamier” and the workflow shifts, instantly and reversibly.
MIT ★ 24 -
Local-first MCP server that drafts ComfyUI workflows a human can actually read - organized, labeled, validated, and test-rendered against your own instance
pypi MIT ★ 2 -
DSH ⇄ ComfyUI 生成链路:自然语言设计可运行 ComfyUI 工作流 → 表单确认 → 运行 → 产物回显。内嵌 comfy-mcp 服务端 + MCP 宿主 + DSH 插件,AI 研发产品(MIT)。
MIT ★ 1 -
MCP server for generating images on ComfyUI from a chat client.
GPL-3.0 -
MCP server for ComfyUI — 50+ tools for node discovery, dynamic workflow builder, WebSocket execution, templates & model management. Works with Claude & Cursor.
MIT ★ 4 -
MCP-first control plane for supported ComfyUI workflows with cryptographic model identity, explicit approvals, durable evidence, and no silent downloads.
MIT ★ 1 -
Zero-GPU-idle gateway for running ComfyUI on ephemeral Google Colab VMs with Zero-Trust Access
MIT ★ 135 -
Local FLUX 3 Image Klein image generation for coding agents: Claude Code plugin (skill + MCP tool) and CLI over headless ComfyUI. Runs on 8 GB GPUs.
MIT -
🎨 Turn Claude Code and OpenClaw into a powerful design assistant with local ComfyUI, API integration, and a large pro prompt library.
MIT ★ 9 -
Generate images and video with Google Gemini, Veo, Runway, Kling, a local ComfyUI, Lemonade, FLUX, Stability AI or OpenAI — a CLI and an MCP server
Apache-2.0 -
An MCP server that turns your own ComfyUI workflows into an image-generation tool for any MCP client: Claude Code, Claude Desktop, Cursor, VS Code, Codex CLI, Gemini CLI and others. ComfyUI can run on the same machine or on a GPU box elsewhere on your LAN. You need no API key and pay nothing per image.
MIT -
Private MCP server for your own ComfyUI: one-shot images (Qwen Image 2.1) and video with sound (MiniMax H3) from Claude Code, Codex or any MCP client. Nothing left on the server.
MIT -
MCP server for ComfyUI: seed knowledge base (62+ nodes), 40 tools for workflow building, real-time execution (WebSocket), batch/chain, model management. For Cursor and Claude.
npm MIT -
Local MCP tools for LM Studio and Ollama: a ComfyUI image-generation server, an MCP smoke-test tool, and setup guides for document, Git, filesystem and browser servers
MIT ★ 1 -
Production diagnostics, analytical VRAM budgeting, ComfyUI/CLI compiler, and Model Context Protocol (FastMCP) bridge for Wan-Video (Wan2.1 & Wan2.2 MoE).
Apache-2.0 -
Local-GPU sprite studio for games: text → transparent RGBA sprites, character bibles & LoRAs. One backend, two faces — a human WebUI and a 15-tool MCP server (ComfyUI-backed).
MIT ★ 4 -
Local-first desktop studio for ComfyUI, built for AI short-drama production - zero-dependency 10MB exe: creation, gallery, 600+ templates, model hub, character assets (LoRA binding), episodic pipeline, MCP server
MIT ★ 33 -
给任何 MCP 客户端装上 350+ 多模态模型:npx -y runninghub-mcp@latest 一条命令接入图像/视频/音频/3D 生成 + ComfyUI 工作流 + AI 应用 + LLM 对话。零构建,--scope 裁剪。适配 WorkBuddy/Claude Desktop/Cursor/OpenClaw。开发者 AI芳程式,反馈 zzdh518
MIT ★ 1 -
Autonomous AI Video Director MCP Server & Production Pipeline for ComfyUI (MiniMax H3, Krea 2, Qwen 2.1) — End-to-end scenario, multi-reference asset pool, 7+1 video generation, and one-look review.
★ 1 -
A local music video pipeline for ComfyUI that any agent can drive: Flux 3 Klein stills and character sheets, LTX 2.3 video, MiniMax Music 3 songs, edit, grade and overlay, plus an MCP server.
Apache-2.0 ★ 3 -
A self-hosted MCP server that can expose local media-generation backends such as ComfyUI and Blender while also providing local media analysis, editing, FFmpeg, HyperFrames, timeline, subtitle, speech, and audio utilities. The project is designed for Portainer-only deployments
Apache-2.0 -
AI design agent that explores Pinterest by itself and makes aesthetic Instagram posts, stories, posters & carousels. Agent Skill + CLI + MCP server for Claude Code, Codex, Gemini CLI. Works with gpt-image, Nano Banana, Flux, ComfyUI.
NOASSERTION ★ 1 -
ComfyUI workflows and GPU LoRA training in Gemini CLI. AI image models FLUX 2 and Seedream 5.0; AI video models Seedance 2.5, Wan 3.0, Wan 2.2 and LTX 2.5.
MIT -
Free, open-source desktop editor for AI inpainting: select, prompt, get a colour-matched layer. FLUX 3 Image, FLUX.2, GPT Image, Nano Banana, Seedream and Qwen through your API key or your own ComfyUI. Layers, PSD export, MCP.
GPL-3.0 ★ 178 -
Self-hosted AI media studio on a Google Colab L4 GPU: text-to-image, image editing, text-to-video with sound, music, text-to-speech, voice cloning, image-to-3D and Whisper transcription. ComfyUI + web UI + MCP server.
AGPL-3.0 ★ 1 -
comfy-cozygithub.com/josephoibrahim/comfy-cozyupdated this year
AI co-pilot for VFX artists using ComfyUI: 134 MCP tools across 6 swappable LLM providers (incl. any OpenAI-compatible endpoint), zero-LLM artist recipes, a default-deny safety gate, reversible LIVRPS edits, EXR-aware vision, workflow.lock provenance, and durable cross-session learning.
pypi MIT -
Free, open-source AI film studio on your own PC. Recurring characters, MiniMax H3 and Seedance shots, voices, music, a short-film wizard and a real editor, on your ComfyUI or your own cloud GPU. Windows, Mac and Linux, with 216 MCP tools so Claude Code, Codex or Hermes can run it.
MIT ★ 104 -
MCP Server for ComfyUI text to image Workflow
pypi MIT -
Review & approve AI agent task plans in a ComfyUI-style node editor, right in your terminal (MCP server + TUI)
MIT -
claude-imaginegithub.com/prenats/claude-imagineupdated this year
MCP server for generating images in Claude Code — supports local image generation tools like ComfyUI and other backends
MIT ★ 1 -
claude-imaginegithub.com/prenats/claude-imagineupdated this year
MCP server for generating images in Claude Code and Cursor — supports local image generation tools like ComfyUI and other backends
npm MIT -
Badgr — GPU Compute, AI Model Deployment & Agent Executionno update data
**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**
smithery -
Let your chat assistant generate selfies
-
A server using FastMCP framework to generate images based on prompts via a remote Comfy server.
MIT ★ 46 -
Describe a Roblox model in words and get it built from native parts, rigged and ready for Studio.
MIT -
Native Rust MCP server for provider-independent image, video, audio, and 3D generation and editing.
GPL-3.0 ★ 4 -
One MCP server for AI image and video generation across 40+ providers, with your own keys and a local library
MIT ★ 3 -
Design template engine + narrative engine + media pipeline. 17 AI image platforms, 4 narrative models, HTMX Web UI, MCP Server. Pure Go single binary, zero runtime deps.
NOASSERTION ★ 3 -
The home port for your local AI. Zero-install Mac app + MCP server: talk to Claude to discover, download and verify Hugging Face models straight to your own drive. By CAIO Group.
MIT ★ 2 -
Danbooru tag MCP for anime image prompts: exact tags, aliases, WD14 tagger names, wiki disambiguation rules, co-occurrence stats. No API key. Windows 10/11, one-line install.
MIT ★ 1 -
KritaPilot: the Krita MCP server and AI assistant. AI agents (Claude, ChatGPT, Gemini, Cursor) and an AI Chat inside Krita paint, edit and generate art, photos, animation and video - with free models built in.
pypi MIT ★ 1