# ai.roc/mcp

> Use this tool when you need to analyze visual data from various sources, such as images or videos, to detect and recognize objects like faces, license plates, pedestrians, vehicles, and guns. The ai.roc/mcp tool solves problems related to surveillance, security, and data extraction by providing outputs like detected object locations and classifications. It takes in visual data as input and outputs detailed detection results, making it ideal for applications in security, law enforcement, and intelligent transportation systems.

Canonical page: https://skillsregistry.net/skills/ai-roc-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ai-roc-mcp

## Description

ROC biometrics & computer vision: face, LPR, OCR, pedestrian, vehicle, gun detection.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.1.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-05-15

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.roc%2Fmcp)

## Use it

MCP endpoint published by the skill: `https://mcp.roc.ai/mcp`

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ai-roc-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ai-roc-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ai-roc-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt