video-analytics

Retrieve video analytics incidents, alerts, and metrics from Elasticsearch via VA-MCP.

Updated May 23, 2026

Search Tags:#metrics #time series #alerts #incidents #elasticsearch #video analytics #mcp json-rpc

Ready to run

npx skills add https://github.com/yo-steven/skills-exploration-20260522 --skill video-analytics-yo-steven

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: video-analytics
Source: https://github.com/yo-steven/skills-exploration-20260522/tree/main/skills/video-search-and-summarization/video-analytics
Command: npx skills add https://github.com/yo-steven/skills-exploration-20260522 --skill video-analytics-yo-steven

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you answer questions about video-event safety outcomes by retrieving recorded incidents, alerts, sensor activity, and analytics metrics from Elasticsearch via the VA-MCP server.

Core Features & Use Cases

Incident and alert lookup: Find recent incidents and drill into a specific incident’s details (optionally including object IDs and extra info).
Sensor, place, and signal discovery: List available sensor IDs and places to scope your queries correctly.
Analytics and time-window metrics: Compute summaries such as average people counts, average speeds, and occupancy-like metrics over a time range.
Use Case: When you get a report like “Was there a people-violation event at Entrance A last hour?”, run an incidents query scoped by place/sensor and then request supporting analytics for the same time window.

Quick Start

Ask your system to query the VA-MCP “incidents” endpoint and return the latest 10 incident summaries for all sensors for the current evaluation window.

Frequently Asked Questions about video-analytics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I retrieve video analytics incidents and alerts from Elasticsearch?▼

You retrieve video analytics incidents by querying Elasticsearch through the VA-MCP JSON-RPC server. This requires a two-step MCP workflow: initializing a session ID header, then sending a tools/call request with the appropriate video_analytics_* method and parameters.

Can I compute average speeds and people counts over a specific time range using video sensor signals?▼

Yes, you can compute average speeds and people counts over a specific time range using video sensor signals. The Skill applies analytics methods to calculate occupancy-like statistics and summaries across your specified sensors, places, and time windows.

What do I need to query VA-MCP for recorded safety violations and object metrics?▼

To query VA-MCP for recorded safety violations and object metrics, you need a running VA-MCP JSON-RPC server at port 9901. You must also know your target sensor IDs and places to correctly scope the video_analytics_* method parameters.

How does the two-step MCP workflow function for video analytics lookup?▼

The two-step MCP workflow functions by first sending an initialization request to obtain a session ID header. After initializing the session, you send a tools/call request containing the video_analytics_* method and your query parameters to retrieve the video analytics data.

Are there limitations when drilling into a specific incident's details via the VA-MCP server?▼

When drilling into a specific incident's details via the VA-MCP server, the limitation is that optional data like object IDs and extra info depends on what was originally recorded in Elasticsearch. You must specify these optional parameters in your tools/call request to retrieve the extended information.