# Plasmate

> Use this tool when you need to efficiently process web pages and extract relevant information, as it converts complex HTML into a simplified Semantic Object Model (SOM) with significantly reduced tokens. This headless browser solves problems of data extraction, web scraping, and automation, providing inputs such as web page URLs and outputs like extracted text and links. It is ideal for use cases requiring rapid and accurate web data processing, with native support for browser automation and no API key requirements.

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

## Description

Agent-native headless browser for AI agents. Converts web pages to a Semantic Object Model (SOM) instead of raw HTML — 17x average token reduction across real-world sites (up to 117x on complex pages). Native MCP server with fetch_page, extract_text, extract_links, and full browser automation. No API key required.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/se2mjcclp7)
- **Repository:** <https://github.com/plasmate-labs/plasmate-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": "plasmate-labs-plasmate-mcp"
    }
  }
}
```

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