ComfyUI LLM Party
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deeps
What is ComfyUI LLM Party?
ComfyUI LLM Party is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to llm agent framework in comfyui includes mcp sever, omost,gpt-sovits, chattts,got-ocr2.0, and flux prompt nodes,access to feishu,discord,and adapts to all llms with similar openai / aisuite interfaces,...
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deeps
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx comfyui-llm-partyConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ComfyUI LLM Party
ComfyUI LLM Party is a comprehensive LLM agent framework built as a custom node pack for ComfyUI, enabling visual construction of AI agent workflows with support for dozens of LLM providers, local models, RAG, GraphRAG, MCP protocol integration, and multi-modal capabilities. It connects AI assistants to platforms like Feishu, Discord, and QQ, and supports advanced features including GPT-SoVITS text-to-speech, ChatTTS, GOT-OCR2.0, and FLUX image generation prompt nodes. The MCP server integration allows ComfyUI workflows to expose their capabilities as MCP tools callable from external AI clients.
Prerequisites
- ComfyUI installed and running (stable version recommended)
- Python 3.10 or higher with pip
- An API key for at least one supported LLM provider (OpenAI, Google, Grok, DeepSeek, etc.) or a local model via Ollama
- ComfyUI Manager installed for easy custom node management
- Optional: CUDA-compatible GPU for local model inference
Install via ComfyUI Manager (recommended)
Open ComfyUI Manager in your running ComfyUI instance, search for 'comfyui_LLM_party', and click Install. This handles dependencies automatically.
Install manually via Git
Alternatively, clone the repository directly into ComfyUI's custom_nodes directory.
cd /path/to/ComfyUI/custom_nodes
git clone https://github.com/heshengtao/comfyui_LLM_party.git
cd comfyui_LLM_party
pip install -r requirements.txtConfigure API keys in config.ini
Edit the config.ini file in the comfyui_LLM_party directory to set your LLM provider credentials and optional services.
# config.ini
[default]
language = en_US
fast_installed = False
openai_api_key = your_openai_api_key
base_url = https://api.openai.com/v1/
google_api_key = your_google_api_key
cse_id = your_google_cse_id
bing_api_key = your_bing_api_keyConfigure MCP server connections
Edit the mcp_config.json file in the comfyui_LLM_party directory to add MCP server connections that your ComfyUI workflows can use as tool sources.
{
"mcpServers": {
"everything": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-everything"]
}
}
}Restart ComfyUI and load a starter workflow
Restart ComfyUI to load the new custom nodes. Open a starter workflow from the workflow/ directory in the comfyui_LLM_party folder — templates include API calls, Ollama setup, local/GGUF models, and VLM configurations.
Build an agent workflow using LLM Party nodes
In the ComfyUI canvas, add LLM Party nodes including an LLM API node (for your provider), a tool node (e.g. web search, RAG), and an agent loop node. Connect them to build a visual AI agent pipeline.
ComfyUI LLM Party Examples
Client configuration
MCP client configuration for connecting to ComfyUI LLM Party's MCP server endpoint.
{
"mcpServers": {
"comfyui-llm-party": {
"command": "npx",
"args": ["comfyui-llm-party"],
"env": {
"COMFYUI_URL": "http://localhost:8188"
}
}
}
}Prompts to try
Example prompts for AI agents using ComfyUI LLM Party's multi-modal and tool-calling capabilities.
- "Generate an image with FLUX based on this description and then analyze it with a vision model."
- "Search the web for the latest news about ComfyUI and summarize it using the LLM agent."
- "Use the RAG knowledge base to answer questions about the uploaded documentation."
- "Convert this text to speech using GPT-SoVITS with the configured voice model."
- "Run a GraphRAG query across the knowledge graph to find connections between these topics."Troubleshooting ComfyUI LLM Party
Custom nodes do not appear in ComfyUI after installation
Ensure all Python dependencies were installed: run 'pip install -r requirements.txt' from the comfyui_LLM_party directory using the same Python environment that ComfyUI uses. Restart ComfyUI completely after installation.
LLM API calls fail with 'invalid API key' or connection errors
Verify your credentials in config.ini. The openai_api_key and base_url must match your provider. For Ollama, set base_url to 'http://localhost:11434/v1/' and api_key to 'ollama'. For other providers, set base_url to their OpenAI-compatible endpoint.
GGUF model loading fails or causes out-of-memory errors
Set 'fast_installed = True' in config.ini if you do not need GGUF support, which skips llama-cpp-python installation. If you need GGUF, install the correct llama-cpp-python wheel for your CUDA version separately before installing requirements.txt.
Frequently Asked Questions about ComfyUI LLM Party
What is ComfyUI LLM Party?
ComfyUI LLM Party is a Model Context Protocol (MCP) server that llm agent framework in comfyui includes mcp sever, omost,gpt-sovits, chattts,got-ocr2.0, and flux prompt nodes,access to feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, glm, deeps It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ComfyUI LLM Party?
Follow the installation instructions on the ComfyUI LLM Party GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ComfyUI LLM Party?
ComfyUI LLM Party works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ComfyUI LLM Party free to use?
Yes, ComfyUI LLM Party is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.
ComfyUI LLM Party Alternatives — Similar Coding Agents Servers
Looking for alternatives to ComfyUI LLM Party? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ComfyUI LLM Party 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 LLM Party?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.