# PDF Text Extractor (Ctrio Lab)

> PDF Text Extractor (Ctrio Lab) is a paid MCP server for files and documents. Extract text, Markdown and metadata from PDF links, per document or per page. 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/ctriolab/pdf-text-extractor
- **MCP Registry name:** com.ctriolab/pdf-text-extractor
- **Categories:** files and documents
- **Listing updated:** 2026-11-14

## About

Run on Apify and exposed through Apify's MCP endpoint, this Actor turns PDF links, an uploaded file or links taken from another Actor's dataset into text an LLM or search index can use. It has no browser, proxy or login step and runs on 512 MB.

Two text orders matter in practice: reading order keeps two-column papers in column order, while layout order rebuilds rows by position and separates table cells with tabs, which suits invoices, statements and forms. Markdown output adds headings from larger fonts, bullet lists and, in layout mode, tables.

It does not do OCR. Scanned or image-only PDFs, password-protected files without a password and non-PDF links are reported in the run summary rather than charged. Metadata includes title, author, dates, PDF version, file size and page count.

## Features

- **Document or page rows:** One row per PDF, or one per page for RAG chunks and citations.
- **Page ranges:** Select pages such as 1-3, 7 or 10- to the end.
- **Layout mode for tables:** Keeps table rows on one line with tab-separated cells.
- **Markdown output:** Optional Markdown with headings, lists and tables.
- **PDF metadata:** Returns title, author, creation date, PDF version, file size and page count.
- **Clear failure reports:** Scanned, protected and non-PDF files are listed in the SUMMARY record and not charged.

## Good for

- Prepare PDFs for RAG with page-level chunks
- Pull tables from invoices and bank statements
- Pull text from research papers in column order
- Find which PDFs in a batch are scanned and need OCR

## Install

### Claude Code (Terminal)

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

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

```sh
https://mcp.apify.com?tools=ctriolab/pdf-text-extractor
```

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

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

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

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

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

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

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

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

## FAQ

### Does it do OCR?

No. It reads the text layer only and flags scanned PDFs so you can send them to an OCR tool.

### Can it open password-protected PDFs?

Yes, if you supply the password; otherwise the file is reported and not charged.

### How is it charged?

Per result row: one PDF in document mode or one page in page mode, from about $0.70 per 1,000 rows, plus Apify platform usage.

### What is the default size limit?

Files over 100 MB are skipped by default, configurable with maxFileSizeMb.

### Is PDF Text Extractor (Ctrio Lab) free?

No. PDF Text Extractor (Ctrio Lab) is a paid product.

### How do I add PDF Text Extractor (Ctrio Lab) to Claude Code?

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

### What are the best alternatives to PDF Text Extractor (Ctrio Lab)?

The closest alternatives to PDF Text Extractor (Ctrio Lab) are ASTra, CARTESIAN ECU, Invoices, SigPen and ConvertAudioToText.

## Alternatives

- [ASTra](https://ai-powered.com/mcp/astra): ASTra is a freemium MCP server for files and documents.
- [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.
- [SigPen](https://ai-powered.com/mcp/sigpen): SigPen is a freemium MCP server for files and documents.
- [ConvertAudioToText](https://ai-powered.com/mcp/convertaudiototext): ConvertAudioToText is a freemium MCP server for design and media.
- [WhoScribe](https://ai-powered.com/mcp/whoscribe): WhoScribe is a freemium MCP server for design and media.
- [filex](https://ai-powered.com/mcp/filex): filex is an open-source MCP server for files and documents.
- [DocJacket](https://ai-powered.com/mcp/docjacket): DocJacket is a freemium MCP server for productivity.

---
Source: https://ai-powered.com/mcp/pdf-text-extractor-ctrio-lab
