Skip to main content
Glama
adamanz

Qwen3-VL Video Understanding MCP Server

by adamanz

analyze_video

Analyze video content by extracting key frames and answering questions about actions, objects, and events using a vision-language model.

Instructions

Analyze a video using Qwen3-VL-8B vision-language model on Blaxel. The video must be accessible via a public URL. The model will: 1. Download the video 2. Extract key frames (up to max_frames) 3. Analyze the frames with your question Examples: - "What happens in this video?" - "Summarize the main events" - "What products are shown?" - "Describe the people and their actions"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
video_urlYesURL of the video to analyze (must be publicly accessible)
questionNoQuestion or prompt about the videoDescribe what happens in this video in detail.
max_framesNoMaximum number of frames to extract (1-16)
max_tokensNoMaximum tokens in response

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/adamanz/qwen-video-blaxel-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server