rasterly-mcp

Give any AI agent eyes and a reader for the live web. An MCP server that lets your agent turn a URL into clean Markdown, a screenshot it can actually see, or a PDF — backed by rasterly, a real headless-Chromium rendering API.

Works in any MCP client: Claude Desktop, Claude Code, Cursor, Windsurf, and others.

Tools

Why an agent wants this: a plain fetch() gets you raw HTML that a modern, JS-rendered site won't even populate. read_url runs a real browser and hands back just the article — far fewer tokens, far more signal.

Related MCP server: pagewatch

Install

Get a key at rasterly.dev (free tier: 100 renders/month), then add the server to your MCP client.

Claude Desktop / Claude Code / Cursor — add to your MCP config (claude_desktop_config.json, .mcp.json, or the client's MCP settings):

{
  "mcpServers": {
    "rasterly": {
      "command": "npx",
      "args": ["-y", "rasterly-mcp"],
      "env": { "RASTERLY_API_KEY": "sk_live_your_key" }
    }
  }
}

Restart the client. Your agent now has read_url, capture_url, and url_to_pdf.

Try it

Ask your agent things like:

• "Read https://news.ycombinator.com and summarize the top 3 posts."

• "Screenshot stripe.com and tell me what the hero section says."

• "Turn this docs page into a PDF."

Config

Run standalone

RASTERLY_API_KEY=sk_live_… npx -y rasterly-mcp

MIT · built on rasterly