# Universal Image Generator MCP Server
Multi-provider AI image generation server for MCP clients. Generate high-quality images using Google Gemini, ZHIPU AI CogView-4, or Alibaba Bailian through any MCP-compatible application.
## Features
- **Multi-Provider Support**: Choose between Gemini, ZhipuAI, or Bailian
- **Image Generation**: Text-to-image for all providers
- **Image Transformation**: Edit existing images (Gemini & Bailian only)
- **Smart Language Optimization**: Automatic prompt translation and optimization
- **Local Storage**: Save generated images to your specified directory
## Quick Setup
### 1. Install via uvx
No manual installation required! The server will be automatically downloaded and run.
### 2. Get API Keys
Choose one provider and get an API key:
- **Gemini**: [Google AI Studio](https://aistudio.google.com/apikey)
- **ZhipuAI**: [ZHIPU AI Platform](https://bigmodel.cn/dev/api)
- **Bailian**: [Alibaba DashScope](https://dashscope.aliyun.com)
### 3. Configure MCP Client
Add to your MCP client configuration (e.g., `claude_desktop_config.json`):
```json
{
"mcpServers": {
"universal-image-generator": {
"command": "uvx",
"args": [
"universal-image-generator-mcp"
],
"env": {
"IMAGE_PROVIDER": "zhipuai",
"ZHIPU_API_KEY": "your-api-key-here",
"GEMINI_API_KEY": "your-api-key-here",
"DASHSCOPE_API_KEY": "your-api-key-here",
"OUTPUT_IMAGE_PATH": "/path/to/save/images"
}
}
}
}
```
**Environment Variables:**
- `IMAGE_PROVIDER`: `"gemini"`, `"zhipuai"`, or `"bailian"`
- Set the corresponding API key for your chosen provider
- `OUTPUT_IMAGE_PATH`: Directory to save generated images (optional)
## Available Tools
### `generate_image_from_text`
Create images from text descriptions.
```
generate_image_from_text(prompt: str) -> str
```
### `transform_image_from_encoded` *(Gemini & Bailian only)*
Transform images using base64-encoded image data.
```
transform_image_from_encoded(encoded_image: str, prompt: str) -> str
```
### `transform_image_from_file` *(Gemini & Bailian only)*
Transform existing image files.
```
transform_image_from_file(image_file_path: str, prompt: str) -> str
```
## Usage Examples
Once configured, ask your AI assistant:
- "Generate an image of a sunset over mountains"
- "Create a 3D rendered flying pig in a sci-fi city"
- "Transform this image by adding snow to the scene"
Generated images are saved to your configured output directory.
## Example Output
**Prompt:** "Create a 3D rendered image of a pig with wings and a top hat flying over a futuristic sci-fi city with lots of greenery"
**Transform:** "Add a cute baby whale flying alongside the pig"
## Provider Capabilities
| Provider | Generation | Transformation | Language Optimization |
|----------|------------|----------------|----------------------|
| Gemini | ✅ | ✅ | English prompts |
| ZhipuAI | ✅ | ❌ | Chinese prompts |
| Bailian | ✅ | ✅ | Chinese prompts |
## Development
Test the server locally:
```bash
git clone https://github.com/ECNU3D/universal-image-generator-mcp.git
cd universal-image-generator-mcp
fastmcp dev src/universal_image_generator_mcp/server.py
```
Visit http://localhost:5173/ to use the MCP Inspector for testing.
## License
MIT License
Raw data
{
"_id": null,
"home_page": null,
"name": "universal-image-generator-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "automation, http, llm, mcp",
"author": null,
"author_email": "Tony Wang <shanghaishanghai@yeah.net>",
"download_url": "https://files.pythonhosted.org/packages/b0/44/9feb13f132d08b550d0299f0eccf2c0933b5a71fa0560a921595c4dd8bfc/universal_image_generator_mcp-0.1.2.tar.gz",
"platform": null,
"description": "# Universal Image Generator MCP Server\n\nMulti-provider AI image generation server for MCP clients. Generate high-quality images using Google Gemini, ZHIPU AI CogView-4, or Alibaba Bailian through any MCP-compatible application.\n\n## Features\n\n- **Multi-Provider Support**: Choose between Gemini, ZhipuAI, or Bailian\n- **Image Generation**: Text-to-image for all providers \n- **Image Transformation**: Edit existing images (Gemini & Bailian only)\n- **Smart Language Optimization**: Automatic prompt translation and optimization\n- **Local Storage**: Save generated images to your specified directory\n\n## Quick Setup\n\n### 1. Install via uvx\n\nNo manual installation required! The server will be automatically downloaded and run.\n\n### 2. Get API Keys\n\nChoose one provider and get an API key:\n\n- **Gemini**: [Google AI Studio](https://aistudio.google.com/apikey)\n- **ZhipuAI**: [ZHIPU AI Platform](https://bigmodel.cn/dev/api) \n- **Bailian**: [Alibaba DashScope](https://dashscope.aliyun.com)\n\n### 3. Configure MCP Client\n\nAdd to your MCP client configuration (e.g., `claude_desktop_config.json`):\n\n```json\n{\n \"mcpServers\": {\n \"universal-image-generator\": {\n \"command\": \"uvx\",\n \"args\": [\n \"universal-image-generator-mcp\"\n ],\n \"env\": {\n \"IMAGE_PROVIDER\": \"zhipuai\",\n \"ZHIPU_API_KEY\": \"your-api-key-here\",\n \"GEMINI_API_KEY\": \"your-api-key-here\",\n \"DASHSCOPE_API_KEY\": \"your-api-key-here\",\n \"OUTPUT_IMAGE_PATH\": \"/path/to/save/images\"\n }\n }\n }\n}\n```\n\n**Environment Variables:**\n- `IMAGE_PROVIDER`: `\"gemini\"`, `\"zhipuai\"`, or `\"bailian\"`\n- Set the corresponding API key for your chosen provider\n- `OUTPUT_IMAGE_PATH`: Directory to save generated images (optional)\n\n## Available Tools\n\n### `generate_image_from_text`\nCreate images from text descriptions.\n```\ngenerate_image_from_text(prompt: str) -> str\n```\n\n### `transform_image_from_encoded` *(Gemini & Bailian only)*\nTransform images using base64-encoded image data.\n```\ntransform_image_from_encoded(encoded_image: str, prompt: str) -> str\n```\n\n### `transform_image_from_file` *(Gemini & Bailian only)*\nTransform existing image files.\n```\ntransform_image_from_file(image_file_path: str, prompt: str) -> str\n```\n\n## Usage Examples\n\nOnce configured, ask your AI assistant:\n\n- \"Generate an image of a sunset over mountains\"\n- \"Create a 3D rendered flying pig in a sci-fi city\"\n- \"Transform this image by adding snow to the scene\"\n\nGenerated images are saved to your configured output directory.\n\n## Example Output\n\n**Prompt:** \"Create a 3D rendered image of a pig with wings and a top hat flying over a futuristic sci-fi city with lots of greenery\"\n\n\n\n**Transform:** \"Add a cute baby whale flying alongside the pig\"\n\n\n\n## Provider Capabilities\n\n| Provider | Generation | Transformation | Language Optimization |\n|----------|------------|----------------|----------------------|\n| Gemini | \u2705 | \u2705 | English prompts |\n| ZhipuAI | \u2705 | \u274c | Chinese prompts |\n| Bailian | \u2705 | \u2705 | Chinese prompts |\n\n## Development\n\nTest the server locally:\n```bash\ngit clone https://github.com/ECNU3D/universal-image-generator-mcp.git\ncd universal-image-generator-mcp\nfastmcp dev src/universal_image_generator_mcp/server.py\n```\n\nVisit http://localhost:5173/ to use the MCP Inspector for testing.\n\n## License\n\nMIT License\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Universal Image Generator MCP",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/ECNU3D/universal-image-generator-mcp",
"Issues": "https://github.com/ECNU3D/universal-image-generator-mcp/issues"
},
"split_keywords": [
"automation",
" http",
" llm",
" mcp"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "0635c42ff0dca139b99f0adb58f3a2f8ef4eeddb33a55dca7845801b84528514",
"md5": "f22cb6c476e974b43d72f752c7b847c8",
"sha256": "2c2a79c9d7c765d6c57a14372da90749fe72b082b7510c1b5750f654c87c2a4d"
},
"downloads": -1,
"filename": "universal_image_generator_mcp-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f22cb6c476e974b43d72f752c7b847c8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 23139,
"upload_time": "2025-07-10T01:25:58",
"upload_time_iso_8601": "2025-07-10T01:25:58.398020Z",
"url": "https://files.pythonhosted.org/packages/06/35/c42ff0dca139b99f0adb58f3a2f8ef4eeddb33a55dca7845801b84528514/universal_image_generator_mcp-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "b0449feb13f132d08b550d0299f0eccf2c0933b5a71fa0560a921595c4dd8bfc",
"md5": "66c23a95e4d24d90ecd71b8bc632594f",
"sha256": "7cf92206e29ab2758f0a0a7850acb82fdb5f8f84d714e54fa279f6b710cc22c3"
},
"downloads": -1,
"filename": "universal_image_generator_mcp-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "66c23a95e4d24d90ecd71b8bc632594f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 3209779,
"upload_time": "2025-07-10T01:26:02",
"upload_time_iso_8601": "2025-07-10T01:26:02.050019Z",
"url": "https://files.pythonhosted.org/packages/b0/44/9feb13f132d08b550d0299f0eccf2c0933b5a71fa0560a921595c4dd8bfc/universal_image_generator_mcp-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-10 01:26:02",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ECNU3D",
"github_project": "universal-image-generator-mcp",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "universal-image-generator-mcp"
}
JSON
