# veilbrowser

> veilbrowser — acunningham-ship-it-veilbrowser. Use this tool when you need to automate browser interactions with precision and stealth, solving problems like fragile CSS selector-based automation and lost session data. Veilbrowser drives a real Chrome browser, returning numbered element references from the accessibility tree for reliable interaction. It's ideal for use cases requiring reuse of logged-in sessions or evading anti-automation measures, with capabilities including attachment to already-running Chrome instances.

Canonical page: https://skillsregistry.net/skills/acunningham-ship-it-veilbrowser  
JSON: https://api.skillsregistry.net/v1/skills/acunningham-ship-it-veilbrowser

## Description

Stealth browser automation over raw CDP, driving a real unmodified Chrome with no Playwright or Puppeteer in the stack. Returns numbered element refs from the accessibility tree so a model clicks ref 3 instead of guessing a CSS selector, and can attach to an already-running Chrome to reuse logged-in sessions.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/djqrt2mvv8)
- **Repository:** <https://github.com/acunningham-ship-it/veilbrowser>

## 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": "acunningham-ship-it-veilbrowser"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/acunningham-ship-it-veilbrowser` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/acunningham-ship-it-veilbrowser/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