User idea ("a cat astronaut")
        │
        ▼
  LangChain LCEL chain (Gemini)   →  expands into a detailed, styled prompt
        │
        ▼
  Hugging Face Inference API      →  generates the actual image
        │
        ▼
  Streamlit UI  /  MCP tool call  →  shown to the user or returned to the agent

imaginate/
├── src/
│   ├── prompt_chain.py     # LangChain LCEL: rough idea -> detailed prompt
│   ├── image_gen.py        # Hugging Face Inference API call
│   └── mcp_server.py       # Exposes generate_image_tool as an MCP tool
├── app/
│   └── streamlit_app.py    # UI
├── outputs/                 # generated images land here
├── .env.example
├── .gitignore
├── requirements.txt
└── README.md

streamlit run app/streamlit_app.py

python src/mcp_server.py

{
  "mcpServers": {
    "imaginate": {
      "command": "python",
      "args": ["/absolute/path/to/imaginate/src/mcp_server.py"]
    }
  }
}