MrScraper MCP is answering right now. Last checked 14 min ago. Last commit 22 Oct 2026.
Scraper API for HTML, Markdown, and screenshots, Google search, and account usage for AI agents.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add mrscraper-mcp --transport http https://mcp.mrscraper.com/mcp
https://mcp.mrscraper.com/mcp
[mcp_servers.mrscraper-mcp]
url = "https://mcp.mrscraper.com/mcp"
{
"mcpServers": {
"mrscraper-mcp": {
"url": "https://mcp.mrscraper.com/mcp"
}
}
}
{
"servers": {
"mrscraper-mcp": {
"type": "http",
"url": "https://mcp.mrscraper.com/mcp"
}
}
}
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://mcp.mrscraper.com/mcp | streamable-http | sign-in | 678 ms | 14 min ago |
Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
Web search for agents: page to Markdown, screenshots, news search, metadata, sitemaps and RDAP.
Screenshots and PDFs of web pages or your HTML/Markdown, paid per call in sats. No account.
Web access for AI agents: URL to Markdown, link metadata, screenshots, links and images of any URL.
Web scraping for AI agents: scrape, search, crawl, map any website to markdown + JSON. No browser.
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Capture, OCR-search, and retrieve local Mac screenshots for AI agents through Stashot.
Remote MCP server for HTML-to-PDF and screenshots with OAuth and API-key auth.
Answers built from our own checks of this server.