Enables video and image analysis using Qwen3-VL models deployed on Modal's serverless GPU infrastructure, supporting hours-long video processing, timestamp grounding, OCR in 32 languages, and various analysis tasks including summarization, text extraction, and frame comparison.
Qwen Video Understanding MCP Server
An MCP (Model Context Protocol) server that enables Claude and other AI agents to analyze videos and images using Qwen3-VL deployed on Modal.
Highlights
Hours-long video support with full recall
Timestamp grounding - second-level precision
256K context (expandable to 1M)
32-language OCR support
Free/self-hosted on Modal serverless GPU
Features
Video Analysis: Analyze videos via URL with custom prompts
Image Analysis: Analyze images via URL
Video Summarization: Generate brief, standard, or detailed summaries
Text Extraction: Extract on-screen text and transcribe speech
Video Q&A: Ask specific questions about video content
Frame Comparison: Analyze changes and progression in videos
Architecture
The MCP server acts as a bridge between Claude and your Qwen2.5-VL model deployed on Modal's serverless GPU infrastructure.
Prerequisites
Modal Account: Sign up at modal.com
Deployed Qwen Model: Deploy the video understanding model to Modal (see below)
Python 3.10+
Quick Start
1. Deploy the Model to Modal (if not already done)
2. Install the MCP Server
Or with uv:
3. Configure Environment
4. Add to Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
5. Restart Claude Desktop
The qwen-video tools should now be available.
Available Tools
analyze_video
Analyze a video with a custom prompt.
analyze_image
Analyze an image with a custom prompt.
summarize_video
Generate a video summary in different styles.
extract_video_text
Extract text and transcribe speech from a video.
video_qa
Ask specific questions about a video.
compare_video_frames
Analyze changes throughout a video.
check_endpoint_status
Check the Modal endpoint configuration.
list_capabilities
List all server capabilities and supported formats.
Configuration
Environment Variable | Description | Default |
| Your Modal workspace/username |
|
| Name of the Modal app |
|
| Override image endpoint URL | Auto-generated |
| Override video endpoint URL | Auto-generated |
Supported Formats
Video: mp4, webm, mov, avi, mkv
Image: jpg, jpeg, png, gif, webp, bmp
Limitations
Videos must be accessible via public URL
Maximum 64 frames extracted per video
Recommended video length: under 10 minutes for best results
First request may have cold start delay (Modal serverless)
Cost
The Modal backend uses A100-40GB GPUs:
~$3.30/hour while processing
Scales to zero when idle (no cost)
Only charged for actual processing time
Troubleshooting
"Request timed out"
Video may be too large
Try a shorter video or reduce
max_frames
"HTTP error 502/503"
Modal container is starting up (cold start)
Wait a few seconds and retry
"Video URL not accessible"
Ensure the URL is publicly accessible
Check for authentication requirements
Development
License
MIT