# Inkpluck: Article Extractor — URL to Text, Markdown & Metadata

> Inkpluck: Article Extractor — URL to Text, Markdown & Metadata is a paid MCP server for files and documents. Turn article URLs or RSS feeds into clean text, Markdown and metadata, $1 per 1,000. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API, Web
- **Website:** https://apify.com/cybermax/article-extract
- **Repository:** https://github.com/cybermax-tools/product-factory
- **MCP Registry name:** io.github.CyberMax-tools/article-extract
- **Categories:** files and documents, web search and scraping, news and media
- **Listing updated:** 2026-11-16

## About

Positioned as a maintained successor to newspaper3k, this tool runs on Apify and is reached through Apify's MCP endpoint scoped to one actor. Input is article URLs or RSS and Atom feeds; output per URL is title, authors, publish and modified dates, language, site name, top image, a paywall flag, word count and reading time, plus plain text and a Markdown version with links and tables. A newspaper3k-compatible field mode adds the old field names.

Extraction uses Mozilla Readability for the body and publisher metadata such as schema.org JSON-LD, OpenGraph and similar meta tags for authors and dates, normalised to ISO 8601 UTC. It uses plain HTTP rather than a headless browser, so a typical article takes about 0.5 to 3 seconds. Home and section pages are flagged as not articles, and paywalls are flagged rather than bypassed. A blocked request is retried once through Apify Proxy.

Monitor mode with feed URLs returns each new article once, which suits a scheduled daily feed. Pricing is $0.001 per extracted article; failed, blocked, paywalled and too-thin pages are free. A free Apify account includes $5 of monthly credit, about 5,000 articles by the listing's estimate.

## Features

- **Text and Markdown output:** Clean text plus a Markdown version with links and tables, without ads or navigation.
- **Publisher metadata:** Authors, dates, language and top image from JSON-LD and meta tags.
- **Paywall flag:** Marks subscriber-only articles instead of hiding them.
- **Feed monitoring:** Process RSS or Atom feeds and return only articles not seen before.
- **Article detection:** Flags home and section pages so they can be skipped for free.
- **newspaper3k fields:** Optional output with the older library's field names.
- **Bring your own HTML:** Pass HTML documents to extract without fetching.

## Good for

- Feed clean article text into an LLM or RAG index
- Build a daily new-articles feed from RSS sources
- Replace an unmaintained newspaper3k pipeline
- Collect a news corpus with authors and dates
- Filter crawled link lists down to real articles

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http article-extract 'https://mcp.apify.com?tools=cybermax/article-extract'
```

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

```sh
https://mcp.apify.com?tools=cybermax/article-extract
```

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

```json
{
  "mcpServers": {
    "article-extract": {
      "url": "https://mcp.apify.com?tools=cybermax/article-extract"
    }
  }
}
```

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

```json
{
  "servers": {
    "article-extract": {
      "type": "http",
      "url": "https://mcp.apify.com?tools=cybermax/article-extract"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "article-extract": {
      "serverUrl": "https://mcp.apify.com?tools=cybermax/article-extract"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "article-extract": {
      "type": "http",
      "url": "https://mcp.apify.com?tools=cybermax/article-extract"
    }
  }
}
```

## FAQ

### How much does it cost?

$0.001 per extracted article, with failed, blocked, paywalled and too-thin pages free.

### Does it use a headless browser?

No. It uses plain HTTP, and JavaScript-only pages are not extracted.

### Can it bypass paywalls?

No. It flags paywalled articles and does not charge for teaser-only pages.

### Is it a replacement for newspaper3k?

The listing describes it as a maintained successor with the same field names available.

### Is Inkpluck: Article Extractor — URL to Text, Markdown & Metadata free?

No. Inkpluck: Article Extractor — URL to Text, Markdown & Metadata is a paid product.

### How do I add Inkpluck: Article Extractor — URL to Text, Markdown & Metadata to Claude Code?

Run this command in your terminal: claude mcp add --transport http article-extract 'https://mcp.apify.com?tools=cybermax/article-extract'

### What are the best alternatives to Inkpluck: Article Extractor — URL to Text, Markdown & Metadata?

The closest alternatives to Inkpluck: Article Extractor — URL to Text, Markdown & Metadata are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and ASTra.

## 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.
- [ASTra](https://ai-powered.com/mcp/astra): ASTra is a freemium MCP server for files and documents.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [CARTESIAN ECU](https://ai-powered.com/mcp/cartesian-ecu): CARTESIAN ECU is a paid MCP server for files and documents.
- [Invoices](https://ai-powered.com/mcp/invoices): Invoices is a paid MCP server for files and documents.

---
Source: https://ai-powered.com/mcp/inkpluck-article-extractor-url-to-text-markdown-and-metadata-2
