Scrapfly runs on your own machine — the client starts it, so there is no endpoint to ping. 59 installs a week from npm. Last commit 11 Sep 2026.
Scrape any website, extract structured data, and collect web content at scale with AI agents
Today is the operative word: we check Scrapfly every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp -- npx -y scrapfly-mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"scrapfly-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "scrapfly-mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"scrapfly-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"scrapfly-mcp"
],
"command": "npx"
}
}
}
Scrape, crawl, and extract structured data from websites at scale
Web scraping MCP server — scrape, extract structured data, screenshot any site with anti-bot bypass.
Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.
Scrape webpages, handle JavaScript and CAPTCHA, extract structured data
Turn any website into structured JSON data matching your custom schema.
Extract data from any website with this web scraper tool.
Web-scraping toolkit with 22 tools for structured web data as JSON for AI agents.
Call 120+ AI models and live web context (scrape/crawl/extract) from any MCP client with one key
Answers built from our own checks of this server.