# Web Scraping

> Web Scraping is an MCP server for web search and scraping. Map a site, scrape pages to markdown or JSON, and search the web from an AI client. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Starting price:** $49 a month
- **Platforms:** Web, API
- **Website:** https://superagnt.com/r/reg-web-scraping-docs
- **Repository:** https://github.com/superagnt/plugins
- **MCP Registry name:** com.superagnt/web-scraping
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-15

## About

Scraping here is two steps by design. You map a site to get its URLs, then pick pages to scrape; it does not crawl a whole site by itself. It reads public pages only and never logs in, submits forms or buys anything.

A page can come back as markdown, a summary, links, images, raw HTML or JSON extracted to a schema you supply. superagnt reports that on ten well-known pages, markdown was a median 25 times smaller than the raw HTML, which keeps model context cheap. Web search results can include page content.

The page's example calls are map and scrape actions at about $0.00144 each. Billing runs through superagnt credits, with a no-card trial of $3 and plans from $49 a month.

## Features

- **Site mapping:** Lists a site's URLs, optionally filtered by search term.
- **Page scraping:** Returns markdown, summary, links, images, HTML or schema-based JSON.
- **Web search:** Returns results along with their content.
- **No browser to run:** Runs on superagnt's side without your own proxy.
- **Public pages only:** Never logs in or submits forms.

## Good for

- Turn documentation pages into markdown for an agent
- Extract structured data to a JSON schema
- Find pages on a site before scraping
- Research a topic with search results and content

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http web-scraping https://mcp.superagnt.com/mcp/web-scraping
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.superagnt.com/mcp/web-scraping
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "web-scraping": {
      "url": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "web-scraping": {
      "type": "http",
      "url": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "web-scraping": {
      "serverUrl": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "web-scraping": {
      "type": "http",
      "url": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}
```

## Tools

- `data_web_map`: Maps a site's URLs.
- `data_web_scrape`: Scrapes a page to the requested formats.

## FAQ

### Can it crawl a whole site?

No. You map first, then choose pages to scrape.

### Can it log in to sites?

No, it reads public pages only.

### What formats can it return?

Markdown, summary, links, images, raw HTML or JSON to your schema.

### What does it cost?

The sample map and scrape calls were about $0.00144 each at list price.

### Is Web Scraping free?

Web Scraping is a paid product with a free trial. Paid plans start at $49 a month.

### How do I add Web Scraping to Claude Code?

Run this command in your terminal: claude mcp add --transport http web-scraping https://mcp.superagnt.com/mcp/web-scraping

### What are the best alternatives to Web Scraping?

The closest alternatives to Web Scraping are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [Shopify MCP Server (any store)](https://ai-powered.com/mcp/shopify-mcp-server-any-store): Shopify MCP Server (any store) is a paid MCP server for e-commerce.
- [Chanroll: YouTube Channel Video Scraper (Official API)](https://ai-powered.com/mcp/chanroll-youtube-channel-video-scraper-official-api): Chanroll: YouTube Channel Video Scraper (Official API) is a paid MCP server for design and media.
- [Vidvett: YouTube Video Details Scraper (Official API)](https://ai-powered.com/mcp/vidvett-youtube-video-details-scraper-official-api): Vidvett: YouTube Video Details Scraper (Official API) is a paid MCP server for design and media.

---
Source: https://ai-powered.com/mcp/web-scraping
