# unbrowser by Unchained

> Use this tool when you need to browse the web in a lightweight and efficient manner, particularly for large language model (LLM) agents, to solve problems such as accessing web content with low overhead and bounded JavaScript execution. It takes in URLs and other browser inputs, and outputs rendered web pages with features like forms, cookies, and escalation hints. Ideal for use cases where a full-fledged browser like Chrome is not required, but still provides an option to escalate to real Chrome via Unchained when needed.

Canonical page: https://skillsregistry.net/skills/protostatis-dev-unbrowser  
JSON: https://api.skillsregistry.net/v1/skills/protostatis-dev-unbrowser

## Description

Lightweight MCP browser for LLM agents. One native binary, no Chrome, low-token BlockMaps, stateful sessions, bounded JavaScript execution, forms, cookies, and escalation hints to real Chrome via Unchained. Hosted endpoint is for public discovery and smoke tests only.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/protostatis-dev/unbrowser)

## 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": "protostatis-dev-unbrowser"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/protostatis-dev-unbrowser` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/protostatis-dev-unbrowser/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