# WebExtract

> WebExtract is a freemium MCP server for web search and scraping. Turn any web page into clean Markdown plus product, table and metadata JSON. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API
- **Website:** https://webextract.dev
- **Repository:** https://github.com/nyx464664816-stack/webextract
- **MCP Registry name:** dev.webextract/extract
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-14

## About

One call returns a page's main content as Markdown and a fixed-schema JSON with product, tables and article metadata, with the same shape on every site. Product data includes name, brand, SKU or GTIN, price, currency, availability and rating, and price_detail is never 0: an unknown price is flagged as unresolved with a reason. Tables come back with row counts, column counts and a consistent-width check.

The free tier gives 20 calls a day per IP with no signup. Prepaid credits never expire and failed fetches are not charged; x402 USDC on 7 chains or Stripe credits can be used. The page is fetched as raw HTML, so JavaScript-built pages may come back thin, and robots.txt is respected.

The /v1/markdown route returns Markdown, title and word count at a lower price. MIT-licensed SDKs exist for npm and PyPI, and there is a LangChain package.

## Features

- **Markdown extraction:** Main content without navigation, ads or scripts.
- **Product fields:** Price, SKU, availability and rating in a fixed schema.
- **Table extraction:** Headers and rows with consistency checks.
- **Page metadata:** Title, authors, dates, canonical URL and language.
- **Free daily calls:** 20 per IP, no signup.

## Good for

- Feed clean page text into a RAG pipeline
- Read product price and availability from a store page
- Pull tables from a report page
- Collect article metadata

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http extract https://api.webextract.dev/mcp
```

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

```sh
https://api.webextract.dev/mcp
```

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

```json
{
  "mcpServers": {
    "extract": {
      "url": "https://api.webextract.dev/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "extract": {
      "type": "http",
      "url": "https://api.webextract.dev/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "extract": {
      "serverUrl": "https://api.webextract.dev/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "extract": {
      "type": "http",
      "url": "https://api.webextract.dev/mcp"
    }
  }
}
```

## FAQ

### Is there a free tier?

Yes, 20 calls a day per IP.

### Does it run JavaScript?

Not yet; raw HTML only.

### Are failed fetches billed?

No.

### Does it respect robots.txt?

Yes.

### Is WebExtract free?

WebExtract has a free plan, with paid plans for more usage or features.

### How do I add WebExtract to Claude Code?

Run this command in your terminal: claude mcp add --transport http extract https://api.webextract.dev/mcp

### What are the best alternatives to WebExtract?

The closest alternatives to WebExtract 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/webextract
