Urlbox is answering right now. Last checked moments ago. 14 installs a week from npm. Last commit 13 Oct 2026.
Screenshots, PDFs, video, markdown and page data from any website, via Urlbox.
Today is the operative word: we check Urlbox every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add screenshot-mcp-server --transport http https://api.urlbox.com/mcp
{
"mcpServers": {
"screenshot-mcp-server": {
"url": "https://api.urlbox.com/mcp"
}
}
}
[mcp_servers.screenshot-mcp-server]
url = "https://api.urlbox.com/mcp"
{
"mcpServers": {
"screenshot-mcp-server": {
"url": "https://api.urlbox.com/mcp"
}
}
}
{
"mcpServers": {
"screenshot-mcp-server": {
"url": "https://api.urlbox.com/mcp"
}
}
}
This one needs environment variables set before it will start:
URLBOX_API_KEY (Urlbox organisation API key (all tools) or project secret key (rendering tools).), URLBOX_DOWNLOAD_DIR (Folder where save_render saves files. Defaults to ~/Downloads.).
The author declared them in the registry entry; get the values from the project itself.
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.urlbox.com/mcp | streamable-http | sign-in | 245 ms | 0 min ago |
Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
Screenshot, PDF, and markdown extraction from any URL via Claude Desktop and Claude Code.
Capture website screenshots from any MCP client via the ScreenshotRender API.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.
Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.
Web access for AI agents: URL to Markdown, link metadata, screenshots, links and images of any URL.
Screenshots of any public web page as PNG, JPEG, WebP, PDF or a scrolling video.
Answers built from our own checks of this server.