← 返回 Skills 市场
71
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ntriq-video-intelligence-mcp
功能描述
Video analysis: object detection, scene classification, activity recognition, and summarization.
安全使用建议
This skill appears to call a third‑party paid API to analyze videos. Before installing or using it: 1) Do not send sensitive or private videos until you confirm the provider's privacy, retention, and security policies. 2) Ask the author how payment is performed and what credentials (if any) will be required — the skill currently lacks billing/auth instructions. 3) Verify the domain (x402.ntriq.co.kr) and service reputation, TLS cert, and terms of service. 4) If you must test it, use non-sensitive sample videos and monitor network calls. 5) If you need on‑device or private processing, prefer skills that explicitly support local processing or that provide clear enterprise/compliance controls. If the author can provide API docs showing authentication and data-retention policies, that would reduce the concerns.
功能分析
Type: OpenClaw Skill
Name: ntriq-video-intelligence-mcp
Version: 1.0.0
The skill bundle contains only metadata and documentation for a video intelligence API service. It defines an interface for object detection and scene analysis via an external endpoint (https://x402.ntriq.co.kr/video-intel-mcp) and includes no executable code, suspicious instructions, or indicators of malicious intent.
能力标签
能力评估
Purpose & Capability
Name, description, and runtime instructions all describe a remote video-analysis API and the SKILL.md shows expected input (video_url) and outputs; requesting no local binaries or installs is consistent with an API-only skill.
Instruction Scope
The instructions direct the agent to POST video data (via a video_url) to an external endpoint (https://x402.ntriq.co.kr/video-intel-mcp). That is expected for a hosted video-intel service, but the skill does not document how video content is authenticated/paid for or whether videos are stored/retained — which creates a privacy/exfiltration risk if the agent sends sensitive user videos to an unknown third party.
Install Mechanism
No install spec and no code files — lowest-risk install surface. Nothing is downloaded or written to disk by the skill itself.
Credentials
SKILL.md advertises a paid endpoint (USDC on Base, $0.05 per call) but the skill declares no required credentials, wallet integration details, API key, or billing environment variables. This mismatch is unexplained: the agent would need a payment mechanism (wallet/private key, signing proxy, or API key) to actually call the paid endpoint, but the skill provides no guidance or required env vars for that.
Persistence & Privilege
Skill does not request persistent presence (always:false) and does not modify system or other skills. Autonomous invocation is allowed (default) but not an additional privilege in itself.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install ntriq-video-intelligence-mcp - 安装完成后,直接呼叫该 Skill 的名称或使用
/ntriq-video-intelligence-mcp触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of ntriq-video-intelligence-mcp.
- Provides object detection, scene classification, activity recognition, and video summarization with timestamped outputs.
- Supports flexible analysis tasks and adjustable parameters (confidence threshold, frame sample rate).
- Returns executive summaries and structured detection results for a wide range of video content.
- Designed for use cases such as security automation, content moderation, and highlight identification.
- Accessible via x402 micropayment API endpoint.
元数据
常见问题
Ntriq Video Intelligence Mcp 是什么?
Video analysis: object detection, scene classification, activity recognition, and summarization. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 71 次。
如何安装 Ntriq Video Intelligence Mcp?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ntriq-video-intelligence-mcp」即可一键安装,无需额外配置。
Ntriq Video Intelligence Mcp 是免费的吗?
是的,Ntriq Video Intelligence Mcp 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Ntriq Video Intelligence Mcp 支持哪些平台?
Ntriq Video Intelligence Mcp 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Ntriq Video Intelligence Mcp?
由 ntriq(@ntriq-gh)开发并维护,当前版本 v1.0.0。
推荐 Skills