vision-mcp
by Pelican0126
Gives text-only coding agents the ability to 'see' images, videos, and screenshots by routing them to a vision model and returning structured text.
Details
- Publisher
- Pelican0126
- Status
- active
by Pelican0126
Gives text-only coding agents the ability to 'see' images, videos, and screenshots by routing them to a vision model and returning structured text.