# fantoma

> fantoma — huzy85-fantoma. Use this tool when you need to access and read website content in Markdown format without relying on large language models or exposing sensitive information. Fantoma solves the problem of secure and private browsing for AI agents, allowing them to log in to sites and access content locally. It takes in website URLs and outputs Markdown-formatted content, making it ideal for use cases where data privacy and efficiency are crucial.

Canonical page: https://skillsregistry.net/skills/huzy85-fantoma  
JSON: https://api.skillsregistry.net/v1/skills/huzy85-fantoma

## Description

Stealth browser for AI agents that runs on small local models. Read any site as Markdown, log in without an LLM, MCP server included.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-24

## Source

- **Source listing:** [GitHub](https://github.com/Huzy85/fantoma)

## 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": "huzy85-fantoma"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/huzy85-fantoma` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/huzy85-fantoma/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