# ATH-MaaS/Pixelle-MCP

An Open-Source Multimodal AIGC Solution based on ComfyUI + MCP + LLM  https://pixelle.ai

Repository: https://github.com/ATH-MaaS/Pixelle-MCP
Canonical: https://ross.abutalabs.com/products/pixelle-mcp
Language: Python
License: MIT
License Family: permissive
Last push: 2025-12-17T07:18:03+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 35, longevity 28
- inputs: {"age_days": 402, "days_push": 259, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1104, forks 150 (observed 2026-08-28T04:03:36.218813+00:00)

## What it is
Pixelle MCP is an open-source omnimodal AIGC framework that converts ComfyUI workflows (local or RunningHub cloud) into MCP tools with zero code. It bundles an MCP server, a Chainlit-based multimodal chat web interface, file services, and multi-LLM integration into a single deployable Python application.

## Use cases
- turn ComfyUI workflows into MCP tools for Claude Desktop or Cursor
- generate images, video, and speech from text via an AI agent
- run a self-hosted multimodal AI chat server
- use cloud ComfyUI without a local GPU
- build an MCP server exposing AIGC capabilities
- chat with an LLM that can call image/audio/video generation tools
- deploy an AIGC service with Docker or pip

## When to choose
- you want MCP-compatible multimodal generation tools without writing code
- you already use ComfyUI workflows and want them callable by LLM agents
- you need a self-hosted chat UI wired to multiple LLM providers and AIGC backends

## When to avoid
- you need a lightweight library to embed in your own app rather than a full server
- you have no ComfyUI workflows and no interest in AIGC generation
- you require non-Python runtimes or managed cloud deployment out of the box

## Facets
- artifact type: framework
- maturity: active
- function: mcp, agent-framework, llm-inference, image-processing, video-processing, speech-recognition, tts, chat-interface, file-upload, cli, web-framework
- domain: artificial-intelligence, large-language-models, image-processing, chatbots, self-hosted, developer-tools
- platform: python, self-hosted, cli, cross-platform
- tags: comfyui, aigc, workflow-as-tool, mcp-server, chainlit, litellm, runninghub, multimodal, zero-code, text-to-image, text-to-video, text-to-speech, ai-agents, video, audio, docker, web-server, gpu

## Member repositories
- ATH-MaaS/Pixelle-MCP (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.218813+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:44:36.171380+00:00, confidence not recorded.
  - readme: https://github.com/ATH-MaaS/Pixelle-MCP (fetched 2026-08-28T04:03:36.218813+00:00, sha d33a0eeddaf3)
- Data as of 2026-08-30T08:39:29.467469+00:00.