MCP App StoreMCP App Store
from video-search-and-summarization636
Query incidents, alerts and sensor metrics from a VA-MCP Elasticsearch backend (port 9901) to answer questions about violations, counts, speeds, and occupancy.
This skill lets an agent query a VA-MCP stack (Elasticsearch via MCP JSON-RPC on port 9901) for incidents, alerts, sensor lists, FOV histograms and analysis summaries. It provides a required two-step command pattern to initialize a session and then call specific tool methods, ensuring accurate retrieval of recorded events and metrics. Typical outputs include incident lists, per-sensor counts, time-bucketed histograms, and analysis like average people or vehicle counts.
Use this skill when a user asks for recorded video-analytics data such as recent incidents, confirmed alerts, object counts, average speeds, or occupancy for specific sensors or places. It's intended for environments where the VA-MCP alerts profile is running and reachable at the host's port 9901.
Best used with agents or harnesses that can run shell commands and curl (CLI-capable agents like Copilot/Codex/Claude Code/CLI-based assistants).
NVIDIA Video Analytics skill for querying incidents, alerts, and sensor metrics from a VA-MCP Elasticsearch backend via JSON-RPC on port 9901. The SKILL.md is well-documented with clear two-step curl patterns and a full tool reference. However, it requires a specific NVIDIA VSS deployment with the alerts profile running, making it very niche. No bundled scripts — purely instruction-based via curl commands. Shell variable interpolation in curl commands poses minor injection risk if HOST_IP or session IDs are untrusted.
Clean skill from a reputable source (NVIDIA). No malicious patterns. Deductions: unquoted variable interpolation in curl commands (-12), no scripts to test (neutral), highly specific infrastructure prerequisite limits broad usefulness. The two-step session pattern is well-documented but adds complexity. No telemetry, no exfiltration, no destructive commands.
AWP (Agent Work Protocol)
Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail
Monitoring Stack Deployer
Deploy and configure production-ready monitoring stacks (Prometheus, Grafana, Datadog) with collectors, dashboards, and alerting rules for Kubernetes, Docker, o
Azure External Attack Surface Management
Provides expert guidance for Azure External Attack Surface Management (EASM): quotas, configuration, integrations, and exporting inventory to analytics platform
Smalltalk MCP
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
