# PDF to Text and Markdown Extractor with Reading Order

> PDF to Text and Markdown Extractor with Reading Order is a paid MCP server for files and documents. Apify Actor that extracts PDF text as Markdown by page, document or chunk, in order. 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/bepolabs/pdf-to-text
- **MCP Registry name:** io.github.bepolabs/pdf-to-text
- **Categories:** files and documents, developer tools
- **Listing updated:** 2026-11-15

## About

Reading order is what sets this extractor apart: two- and three-column pages are read in sequence, running headers, footers and page numbers are stripped, and headings and lists are kept as Markdown. Rows can be cut by page, whole document or chunk, with chunks of about 2,000 characters by default ending at paragraph or sentence boundaries and carrying their section path.

Pages with no text layer are flagged with needsOcr instead of returning empty text silently, and each row reports word count and the web links it cites. Inputs are public PDF URLs or files uploaded to the run's key-value store. Defaults cap at 300 pages and 50 MB per file.

It runs on Apify, with MCP access through mcp.apify.com.

## Features

- **Reading-order columns:** Multi-column layouts are read in sequence.
- **Header and footer removal:** Drops lines repeated across pages.
- **Three row shapes:** Page, document or chunk output.
- **Scan detection:** needsOcr marks pages without a text layer.
- **Word count and links:** Per-row counts for RAG sizing and link checks.

## Good for

- Prepare papers and manuals for a vector store
- Index every PDF in an archive
- Pull per-page text from academic papers
- Extract raw text from filings before parsing

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http pdf-to-text 'https://mcp.apify.com?tools=bepolabs/pdf-to-text'
```

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

```sh
https://mcp.apify.com?tools=bepolabs/pdf-to-text
```

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

```json
{
  "mcpServers": {
    "pdf-to-text": {
      "url": "https://mcp.apify.com?tools=bepolabs/pdf-to-text"
    }
  }
}
```

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

```json
{
  "servers": {
    "pdf-to-text": {
      "type": "http",
      "url": "https://mcp.apify.com?tools=bepolabs/pdf-to-text"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "pdf-to-text": {
      "serverUrl": "https://mcp.apify.com?tools=bepolabs/pdf-to-text"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "pdf-to-text": {
      "type": "http",
      "url": "https://mcp.apify.com?tools=bepolabs/pdf-to-text"
    }
  }
}
```

## FAQ

### What does it cost?

$2.80 per 1,000 PDF documents, with 20 pages included each and a small charge per extra page.

### Does it do OCR?

No. It flags pages that need OCR.

### What are the default limits?

300 pages and 50 MB per PDF.

### Are failures charged?

No, failures cost nothing.

### Is PDF to Text and Markdown Extractor with Reading Order free?

No. PDF to Text and Markdown Extractor with Reading Order is a paid product.

### How do I add PDF to Text and Markdown Extractor with Reading Order to Claude Code?

Run this command in your terminal: claude mcp add --transport http pdf-to-text 'https://mcp.apify.com?tools=bepolabs/pdf-to-text'

### What are the best alternatives to PDF to Text and Markdown Extractor with Reading Order?

The closest alternatives to PDF to Text and Markdown Extractor with Reading Order are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/pdf-to-text-and-markdown-extractor-with-reading-order
