Metadata-Version: 2.4
Name: image-mcp-server
Version: 0.1.1
Summary: MCP server for image understanding using Alibaba Cloud's Qwen3-VL-Plus model
Project-URL: Homepage, https://github.com/your-repo/image-mcp-server
Project-URL: Repository, https://github.com/your-repo/image-mcp-server
Project-URL: Documentation, https://github.com/your-repo/image-mcp-server/docs
Project-URL: Bug Tracker, https://github.com/your-repo/image-mcp-server/issues
Author-email: Image MCP Server Contributors <maintainers@example.com>
Maintainer-email: Image MCP Server Contributors <maintainers@example.com>
License: MIT
License-File: LICENSE
Keywords: ai,alibaba-cloud,analysis,dashscope,image,mcp,qwen,vl
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Multimedia :: Graphics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.12
Requires-Dist: fastmcp>=2.12.5
Requires-Dist: httpx[socks]>=0.28.1
Requires-Dist: openai>=2.5.0
Requires-Dist: pillow>=12.0.0
Requires-Dist: pydantic>=2.12.3
Requires-Dist: python-dotenv>=1.1.1
Requires-Dist: tenacity>=9.1.2
Requires-Dist: typer>=0.19.2
Description-Content-Type: text/markdown

# Image MCP Server

A Model Context Protocol (MCP) server for image understanding using Alibaba Cloud's Qwen3-VL-Plus model.

## Quick Start

### Installation

```bash
uvx image-mcp-server
```

### Configuration

Set your DashScope API key:

```bash
export IMAGE_MCP_DASHSCOPE_API_KEY="your-api-key-here"
```

### Usage

The server provides an `analyze_image` tool that can analyze images from URLs or base64 data.

## Development

```bash
# Install in development mode
uv pip install -e .

# Run tests
pytest

# Lint code
ruff check .

# Format code
black .
isort .
```

## License

MIT