mcp-vision

groundlight/mcp-vision

3.5

If you are the rightful owner of mcp-vision and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

mcp-vision is a Model Context Protocol (MCP) server that enhances the vision capabilities of large language or vision-language models by exposing HuggingFace computer vision models as tools.

Tools

Functions exposed to the LLM to take actions

locate_objects

Detect and locate objects in an image using zero-shot object detection pipelines.

zoom_to_object

Zoom into an object in the image, allowing for closer analysis by cropping to the object's bounding box.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources