# screentest-mcp

> screentest-mcp — marilynceo-screentest-mcp. Use this tool when you need to visually test AI agents through automated screenshot capture and comparison. It solves problems such as detecting visual regressions and layout issues by providing pixel-perfect diff and baseline management capabilities. The tool accepts screenshot inputs and outputs diff results, making it ideal for use cases where visual accuracy is crucial, such as during git-based continuous integration pipelines.

Canonical page: https://skillsregistry.net/skills/marilynceo-screentest-mcp  
JSON: https://api.skillsregistry.net/v1/skills/marilynceo-screentest-mcp

## Description

Visual testing for AI agents u2014 screenshot capture, pixel-perfect diff, baseline management, element detection, layout analysis. 7 tools: capture_screenshot, compare_screenshots, set_baseline, check_regression, detect_elements, analyze_layout, batch_test.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/marilynceo/screentest-mcp)

## Use it

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": "marilynceo-screentest-mcp"
    }
  }
}
```

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