bamchi/scrapi-mcp-server

MCP server that converts URLs to clean Markdown/Text for LLM agents

한국어 · Website · Dashboard

⚡ Fast & Reliable — Built on 8+ years of web scraping expertise, 1,900+ production crawlers, and battle-tested anti-bot handling.

What is this?

An MCP (Model Context Protocol) server that lets AI agents fetch and read web pages. Simply give it a URL, and it returns clean, LLM-ready content — fast.

Before: AI can’t read web pages directly
After: “Summarize this article” just works ✨

---

Features

• 🌐 URL → Markdown: Preserves headings, lists, links
• 📄 URL → Text: Plain text extraction
• 🏷️ Metadata: Title, author, date, images
• 🧹 Clean Output: No ads, no navigation, no scripts
• ⚡ JavaScript Rendering: Works with SPAs
• 💳 Built-in Billing: Credit tracking, subscription management, usage analytics (MCP keys)
• 🔄 Auto-Retry: 429 rate limit responses automatically retried with Retry-After
• 🌍 Dual Transport: Stdio (npx) + Streamable HTTP for flexible deployment

---

Transport Modes

Scrapi MCP Server supports two transport modes:

---

Prerequisites

• Scrapi MCP account (separate from the main Scrapi account)
• Claude Desktop, Cline, or Cursor installed
• Node.js 20+

---

Installation

Option A: npx (Recommended)

No installation needed. Just configure your MCP client to use npx.

{
  "mcpServers": {
    "scrapi": {
      "command": "npx",
      "args": ["-y", "@scrapi.ai/mcp-server"],
      "env": {
        "SCRAPI_API_KEY": "your-api-key"
      }
    }
  }
}

Tip: You can also pass the API key via CLI argument instead of env var:

"args": ["-y", "@scrapi.ai/mcp-server", "--api-key", "your-api-key"]

See Step 2 for where to put this configuration.

Option B: Install from Source

# Clone the repository