rasterly-mcp
Enables AI agents to read, screenshot, or convert web pages to PDF using a real headless browser, turning any URL into clean Markdown, a visual image, or a print-ready document.
README
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
| Tool | What the agent gets |
|---|---|
read_url |
The page's main content as clean, LLM-ready Markdown — JS is rendered, nav/ads/boilerplate stripped. Use it to read a URL. |
capture_url |
A screenshot returned as an image, so the agent can see the page (layout, charts, anything visual). full_page optional. |
url_to_pdf |
A print-ready PDF of the page (base64 resource). |
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.
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
| Env var | Default | Notes |
|---|---|---|
RASTERLY_API_KEY |
– | Your rasterly key (sent as X-Api-Key). |
RASTERLY_API_URL |
https://rasterly-production.up.railway.app |
Override to point at a self-hosted rasterly. |
Run standalone
RASTERLY_API_KEY=sk_live_… npx -y rasterly-mcp
MIT · built on rasterly
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.