# chrome-eye

> chrome-eye — trvux-chrome-eye. Use this tool when you need to inspect and interact with a real Chrome browser instance programmatically, leveraging the Chrome DevTools Protocol (CDP) to access structured JSON data without relying on screenshot-based vision loops. It solves problems related to automating browser interactions, debugging, and testing, providing a fast and cost-effective solution. The chrome-eye tool accepts inputs via CDP and outputs structured JSON data, making it ideal for use cases that require seamless browser automation and inspection.

Canonical page: https://skillsregistry.net/skills/trvux-chrome-eye  
JSON: https://api.skillsregistry.net/v1/skills/trvux-chrome-eye

## Description

MCP server giving Claude Code a fast, cheap structured-JSON eye into real Chrome via CDP — no screenshot vision loop

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/trvux/chrome-eye)

## 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": "trvux-chrome-eye"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/trvux-chrome-eye` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/trvux-chrome-eye/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
