ComfyUI Animatool
AI Tool Use API for Anima anime/illustration image generation. Supports MCP Server, HTTP API, and CLI.
What is ComfyUI Animatool?
ComfyUI Animatool is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai tool use api for anima anime/illustration image generation. supports mcp server, http api, and cli.
AI Tool Use API for Anima anime/illustration image generation. Supports MCP Server, HTTP API, and CLI.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI Tool Use API for Anima anime/illustration image generatio
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx comfyui-animatoolConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ComfyUI Animatool
ComfyUI-AnimaTool is an MCP server that connects AI coding assistants directly to ComfyUI running the Anima anime/illustration image generation model. It lets agents like Claude, Cursor, or Gemini generate high-quality anime and illustration images through structured prompts, with the resulting images displayed natively inside the chat window. The server supports structured prompt composition, 14 aspect-ratio presets, batch generation, reroll from history, and model switching, and can be used either as a ComfyUI custom node or as a standalone PyPI package that connects to any running ComfyUI instance over HTTP.
Prerequisites
- ComfyUI installed and running (default: http://127.0.0.1:8188)
- Anima model files downloaded from Hugging Face (circlestone-labs/Anima): anima-preview.safetensors in models/diffusion_models/, qwen_3_06b_base.safetensors in models/text_encoders/, qwen_image_vae.safetensors in models/vae/
- Python 3.10+ with pip, or uv installed for the standalone PyPI package mode
- An MCP-compatible client: Cursor, Claude Desktop, or Cherry Studio (use the preview build for correct image display)
Install ComfyUI and download Anima models
Set up ComfyUI and place the three required Anima model files (UNET, CLIP/text encoder, VAE) into their respective directories under ComfyUI/models/. Download from https://huggingface.co/circlestone-labs/Anima.
Install via ComfyUI Manager (recommended)
Open ComfyUI Manager, search for 'Anima Tool', click Install, and restart ComfyUI. This registers the server as a custom node and starts the HTTP API automatically.
Or install as a standalone PyPI package
For remote or cloud ComfyUI instances, install the standalone package with pip or run it without installation using uvx. This mode connects over the ComfyUI HTTP API and does not require placing files in custom_nodes.
pip install comfyui-animatool
# or run without installing:
uvx --from comfyui-animatool animatool-mcpConfigure your MCP client
Add the AnimaTool MCP server to your client config. Set COMFYUI_URL to wherever your ComfyUI instance is running. For cloud instances behind auth, also set ANIMATOOL_BEARER_TOKEN or ANIMATOOL_HEADERS_JSON.
Restart your client and test image generation
Restart Cursor or Claude Desktop to load the new MCP server. Ask the AI to generate an anime image — the result will display natively in the chat window if your client supports MCP ImageContent.
ComfyUI Animatool Examples
Client configuration
Cursor or Claude Desktop MCP config using uvx to run the standalone comfyui-animatool package, pointing at a local ComfyUI instance.
{
"mcpServers": {
"anima-tool": {
"command": "uvx",
"args": ["--from", "comfyui-animatool", "animatool-mcp"],
"env": {
"COMFYUI_URL": "http://127.0.0.1:8188",
"ANIMATOOL_CHECK_MODELS": "false"
}
}
}
}Prompts to try
Ask your AI assistant to generate anime illustrations. The server handles structured prompt composition and aspect ratio selection automatically.
- "Draw a girl in a white dress in a flower garden, portrait 9:16, safe"
- "Generate a cyberpunk cityscape at night in 21:9 widescreen"
- "Create a batch of 4 anime character portraits with different hair colors"
- "Reroll the last image but change the art style to watercolor"Troubleshooting ComfyUI Animatool
Images display as base64 text instead of rendered pictures
Use the Cherry Studio v1.7.17-preview build (linked in the repo) instead of the official Cherry Studio release. The official build has not yet merged the MCP ImageContent fix. For Cursor, update to a recent version that supports MCP image responses.
Connection refused or ComfyUI URL not reachable
Ensure ComfyUI is running before starting the MCP server. Check that COMFYUI_URL matches the actual host and port (default http://127.0.0.1:8188). For remote instances, verify network access and set ANIMATOOL_BEARER_TOKEN if authentication is required.
Model not found errors on startup
Set ANIMATOOL_CHECK_MODELS=false in the env config to skip the model validation check, or verify that all three Anima model files are placed in the correct ComfyUI model subdirectories as described in the prerequisites.
Frequently Asked Questions about ComfyUI Animatool
What is ComfyUI Animatool?
ComfyUI Animatool is a Model Context Protocol (MCP) server that ai tool use api for anima anime/illustration image generation. supports mcp server, http api, and cli. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ComfyUI Animatool?
Follow the installation instructions on the ComfyUI Animatool GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ComfyUI Animatool?
ComfyUI Animatool works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ComfyUI Animatool free to use?
Yes, ComfyUI Animatool is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.
ComfyUI Animatool Alternatives — Similar Data Science & ML Servers
Looking for alternatives to ComfyUI Animatool? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ComfyUI Animatool in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ComfyUI Animatool?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.