vlm_mcp_server

camillebrl/vlm_mcp_server

3.2

If you are the rightful owner of vlm_mcp_server 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.

A Model Context Protocol (MCP) server for image analysis using the Vision-Language InternVL3 model, enabling image relevance evaluation and text response generation based on visual content.

Tools

Functions exposed to the LLM to take actions

analyze_images_with_query

Analyzes multiple images with automatic relevance verification.

check_image_relevance

Checks if an image is relevant to a query.

analyze_single_image

Provides detailed analysis of a single image.

get_model_status

Retrieves the current status of the model (loaded/unloaded, memory usage).

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources