Scrapi

Name: Scrapi
Author: bamchi

@bamchi

Repository

About Scrapi

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

#web-scraping #scraping #ai-agent #mcp #markdown #anti-bot #llm #streamable-http

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

Scrapes a webpage and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.

Scrapes multiple webpages in parallel and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.

Check API usage and remaining credits. Returns current plan, subscription credits, purchased credits, and total remaining credits.

Check the status of all ScraperServer instances. Shows server health, circuit breaker state, failure counts, and last success/failure times.

Retrieve MCP billing information: subscription details, available plans, daily usage history, or spending limits.

Overview

What is Scrapi?

Scrapi is an MCP server that converts URLs into clean Markdown or plain text for LLM agents, enabling AI tools to fetch and read web pages directly. It is built on 8+ years of web scraping expertise and provides fast, reliable content extraction.

How to use Scrapi?

Install via npx or from source, then configure your MCP client (Claude Desktop, Cline, Cursor, Claude Code) with the provided JSON configuration. Obtain an API key from scrapi.ai/dashboard (free plan available) and set SCRAPI_API_KEY or pass --api-key. Use tools like scrape_url or scrape_urls to fetch content.

Key features of Scrapi

URL to Markdown with preserved headings, lists, links
URL to plain text extraction
Metadata extraction (title, author, date, images)
Clean output – no ads, navigation, or scripts
JavaScript rendering for single-page applications
Built-in billing with credit tracking and subscription management
Auto-retry on 429 rate limit responses
Dual transport: Stdio and Streamable HTTP

Use cases of Scrapi

AI agents summarizing online articles for research
Chatbots retrieving and citing live web content
Automated content monitoring and data gathering
Extracting structured information from documentation pages

FAQ from Scrapi

What does Scrapi do that alternatives don’t?

Scrapi provides clean, LLM-ready Markdown/Text output with JavaScript rendering, metadata, and built-in billing – no need for separate proxies or parsing libraries.

What are the runtime requirements?

A Node.js 20+ environment is needed for Stdio mode; Streamable HTTP transport works without Node.js on the client side.

Where is my data processed and stored?

The README does not specify data storage location; API calls are handled by scrapi.ai servers. Self-hosting the HTTP server is also possible (advanced).

Are there rate limits or usage caps?

Yes. The free plan includes 500 credits per month. Rate limit responses (429) are automatically retried using Retry-After headers.

What authentication does Scrapi use?

Authentication is via an API key (hsmcp_ prefix) set as environment variable SCRAPI_API_KEY or passed as --api-key CLI argument, or via Bearer token header for Streamable HTTP.