Skip to main content
Glama
adamanz

Qwen Video Understanding MCP Server

by adamanz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MODAL_APPYesName of the Modal appqwen-video-understanding
MODAL_WORKSPACEYesYour Modal workspace/usernameadam-31541
QWEN_IMAGE_ENDPOINTNoOverride image endpoint URL (auto-generated if not provided)
QWEN_VIDEO_ENDPOINTNoOverride video endpoint URL (auto-generated if not provided)

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
analyze_videoA

Analyze a video using Qwen3-VL vision-language model.

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

  4. Provide timestamp-grounded responses when applicable

Examples:

  • "What happens in this video?"

  • "Summarize the main events with timestamps"

  • "What products are shown?"

  • "At what timestamp does the speaker mention X?"

  • "What is being discussed or demonstrated?"

analyze_imageA

Analyze an image using Qwen2.5-VL vision-language model.

The image must be accessible via a public URL.

Examples:

  • "What's in this image?"

  • "Describe the scene"

  • "What text is visible?"

  • "Identify any people or objects"

  • "What is the mood or atmosphere?"

summarize_videoC

Generate a summary of a video.

Styles:

  • brief: 1-2 sentence overview

  • standard: 1-2 paragraph summary with key points

  • detailed: Comprehensive analysis with timeline

extract_video_textA

Extract and transcribe any visible text or speech from a video.

Useful for:

  • Reading on-screen text, titles, captions

  • Transcribing spoken content

  • Extracting text from presentations or documents shown in video

video_qaA

Ask a specific question about a video's content.

Examples:

  • "How many people appear in this video?"

  • "What color is the car?"

  • "What is the speaker's main argument?"

  • "What products are being demonstrated?"

  • "At what point does the action begin?"

compare_video_framesB

Analyze changes and progression across a video.

Useful for:

  • Before/after comparisons

  • Tracking movement or changes

  • Understanding progression of events

  • Analyzing tutorials or how-to videos

check_endpoint_statusB

Check the configuration and status of the Modal endpoints.

Returns the configured endpoint URLs and connection status.

list_capabilitiesB

List the capabilities of this video understanding server.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
get_server_infoGet information about this MCP server's capabilities.
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 8 tools

Disambiguation3/5

Most tools have distinct purposes (e.g., analyze_video vs. summarize_video), but some overlap exists: analyze_video and video_qa both handle video Q&A, and extract_video_text could be seen as a subset of analyze_video's capabilities. The descriptions help differentiate, but agents might still misselect between closely related tools.

Naming Consistency4/5

Tools follow a consistent verb_noun pattern (e.g., analyze_image, check_endpoint_status, list_capabilities), with only minor deviations: compare_video_frames uses 'compare' instead of 'analyze' or 'extract', but it's still readable and fits the pattern. Overall, the naming is predictable and clear.

Tool Count5/5

With 8 tools, the count is well-scoped for a video understanding server. Each tool serves a specific function (e.g., analysis, summarization, text extraction), and there are no redundant or trivial additions. This number allows comprehensive coverage without being overwhelming.

Completeness4/5

The toolset covers core video understanding tasks well: analysis, summarization, Q&A, text extraction, and comparison. Minor gaps exist, such as no explicit tool for video editing or metadata retrieval, but agents can work around these with the provided tools. The domain is adequately covered for most use cases.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources