api

An MCP server that provides cloud APIs for understanding images, audio, and video through Qwen media models and DashScope.

In plain words
What is it for?
Use it for image conversations, text recognition, locating objects, video captions with timestamps, speech transcription, speaker separation, event counting, and image or video segmentation.
Why use it?
It provides one interface for media tasks that would otherwise require separate services or model-specific integrations.

Plugin for Claude Code

▶ Qwen Plugins Let Claude Code, Codex & Gemini See, Watch & Build in 3D— MM Plugins Explained Morgans Code · about QwenLM/Qwen-MM-Plugins · on YouTube →
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add QwenLM/Qwen-MM-Plugins
agentmods
npx agentmods add plugins/qwenlm/qwen-mm-plugins/api
Clone the repo
git clone --depth 1 https://github.com/QwenLM/Qwen-MM-Plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

api scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/capabilities/api/.claude-plugin/plugin.json · 19 lines

What it actually says

{
  "name": "qwen-mm-plugins-api",
  "version": "1.0.5",
  "description": "Qwen-MM-Plugins api — cloud APIs for understanding media, by model family: VL (vision chat, OCR, grounding), Omni A/V (timestamped captioning, ASR / multi-speaker diarization, temporal grounding, event counting), plus ASR and segmentation (SAM3), exposed as an MCP server; currently supports DashScope.",
  "skills": [
    "./skill"
  ],
  "mcpServers": {
    "qwen-mm-plugins-api": {
      "command": "uvx",
      "args": [
        "--from",
        "qwen-mm-plugins[api] @ git+https://github.com/QwenLM/[email protected]",
        "qwen-mm-plugins-api"
      ]
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 19 lines scan A a3b06ee7bf85

Subscribe to this mod's changes

api is a plugin published in the GitHub repository QwenLM/Qwen-MM-Plugins (2,795 stars, last pushed 8d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.