# Ghosthand

> Use this tool when you need to automate browser interactions with a human-like touch, evading bot detection and enabling seamless navigation. Ghosthand solves the problem of obvious automated browsing by providing a visible, cursor-driven interface that mimics human behavior. It takes in coding instructions and outputs a natural, undetectable browsing experience.

Canonical page: https://skillsregistry.net/skills/kumard3-ghosthand  
JSON: https://api.skillsregistry.net/v1/skills/kumard3-ghosthand

## Description

Enables MCP-capable coding agents to read and drive the user's browser page with a visible, human-like cursor that evades bot detection.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ubblv7rrb2)
- **Repository:** <https://github.com/kumard3/agentcursor>

## 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": "kumard3-ghosthand"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kumard3-ghosthand` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kumard3-ghosthand/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