Scrapi
@bamchi
Web scraping MCP server for AI agents. Bypass anti-bot systems and get clean, LLM-ready Markdown content. Supports both stdio and Streamable HTTP transports. Built on 8+ years of production scraping infrastructure.
Overview
Scrapi - Web Scraping for AI Agents
Scrapi converts any webpage into clean, LLM-ready Markdown — even sites protected by anti-bot systems like Cloudflare, Akamai, and DataDome.
Tools
| Tool | Description |
|---|---|
scrape_url | Scrape a single URL to Markdown |
scrape_urls | Scrape up to 10 URLs in parallel |
get_usage | Check API credits and usage |
get_billing | View subscription, plans, daily usage |
scraper_server_status | Check scraper health and circuit breaker status |
Quick Start
stdio (npx):
{
"mcpServers": {
"scrapi": {
"command": "npx",
"args": ["-y", "@scrapi.ai/mcp-server"],
"env": {
"SCRAPI_API_KEY": "your-api-key"
}
}
}
}
Streamable HTTP:
{
"mcpServers": {
"scrapi": {
"url": "https://scrapi.ai/mcp",
"headers": {
"Authorization": "Bearer your-api-key"
}
}
}
}
Links
- https://scrapi.ai
- https://github.com/bamchi/scrapi-mcp-server
- https://www.npmjs.com/package/@scrapi.ai/mcp-server
Server Config
{
"mcpServers": {
"scrapi": {
"command": "npx",
"args": [
"-y",
"@scrapi.ai/mcp-server"
],
"env": {
"SCRAPI_API_KEY": "your-api-key"
}
}
}
}