Image-Vision MCP Server
by liunan-githu
Enables text-only language models to 'see' and describe images by calling multimodal APIs (OpenAI, Anthropic) for image analysis.
Details
- Publisher
- liunan-githu
- Status
- active
by liunan-githu
Enables text-only language models to 'see' and describe images by calling multimodal APIs (OpenAI, Anthropic) for image analysis.