# Rove

> Use this tool when you need to automate browser interactions and extract structured data while minimizing token usage. Rove solves problems related to web scraping, accessibility testing, and automated browsing by providing accessibility trees and screenshots via a credit-based pricing model. It takes in navigation and interaction commands via MCP and returns structured data and accessibility trees as output.

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

## Description

Hosted Playwright browser automation for AI agents. Returns accessibility trees instead of screenshots, cutting token usage by 77%. Navigate, interact, extract structured data, and take screenshots — all via MCP. Zero infrastructure, credit-based pricing.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-02

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/sxhg4mww6p)
- **Repository:** <https://github.com/noncelogic/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": "noncelogic-mcp"
    }
  }
}
```

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