# PDF & Office to Markdown for RAG

> PDF & Office to Markdown for RAG is a paid MCP server for files and documents. Converts PDFs, scans and Office files to Markdown with real tables and page-aware chunks. 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/lif_manager/documents-to-markdown-rag
- **Repository:** https://github.com/brunenjere/lif-tools
- **MCP Registry name:** io.github.BrunenJere/documents-to-markdown-rag
- **Categories:** files and documents, knowledge and memory
- **Listing updated:** 2026-11-14

## About

Tables are the focus. They come out as Markdown, CSV and a cell array rather than jumbled lines, and tables whose ruling only separates groups of rows are split back into one row per record. Two- and three-column layouts are read in the right order, repeated headers, footers and page numbers are removed, and paragraphs broken across columns or pages are rejoined.

Chunks follow section boundaries, carry a page range and section path such as Introduction > Method, and repeat the header row when a table has to be split. OCR runs only on pages without a usable text layer, with Spanish and English by default and Portuguese, French, German and Italian available, so text pages stay fast at about 0.2 seconds each. Output can be one item per document, per chunk or per page.

There is no LLM inside: processing uses open-source engines such as pdfplumber, pypdfium2, Tesseract and python-docx inside the Apify container, so documents are not sent to a third-party AI service. Inputs are public URLs or an Apify storage you select, up to 50 MB each, for PDF, PNG, JPG, WEBP, TIFF, BMP, DOCX, XLSX, PPTX (with speaker notes), TXT, MD and CSV. Empty input runs an uncharged demo.

## Features

- **Real table output:** Tables as Markdown, CSV and cell arrays.
- **Reading order:** Multi-column pages are read in the correct sequence.
- **Clean pages:** Repeated headers, footers and page numbers are removed.
- **Section-aware chunks:** Chunks carry page range and section path.
- **Selective OCR:** Only pages without a text layer are scanned.
- **No LLM involved:** Deterministic open-source engines run inside the container.
- **Many formats:** PDF, images, DOCX, XLSX, PPTX, TXT, MD and CSV.

## Good for

- Prepare a report archive for a vector index
- Extract a financial table as CSV from a PDF
- Convert a slide deck including speaker notes
- Make scanned government gazettes searchable
- Feed policy documents to an agent with page citations

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http documents-to-markdown-rag 'https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag'
```

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

```sh
https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag
```

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

```json
{
  "mcpServers": {
    "documents-to-markdown-rag": {
      "url": "https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag"
    }
  }
}
```

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

```json
{
  "servers": {
    "documents-to-markdown-rag": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "documents-to-markdown-rag": {
      "serverUrl": "https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "documents-to-markdown-rag": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag"
    }
  }
}
```

## FAQ

### What does it cost?

Apify lists from $1 per 1,000 pages; the vendor README gives $0.001 per page and $0.003 per OCR page.

### Are my documents sent to an AI service?

No. The page says no third-party AI API is used and processing is deterministic.

### What is the file size limit?

Up to 50 MB each.

### Which OCR languages are available?

Spanish and English by default, plus Portuguese, French, German and Italian.

### How do I call it from an agent?

Use the Apify API or MCP with a documents list of URLs.

### Is PDF & Office to Markdown for RAG free?

No. PDF & Office to Markdown for RAG is a paid product.

### How do I add PDF & Office to Markdown for RAG to Claude Code?

Run this command in your terminal: claude mcp add --transport http documents-to-markdown-rag 'https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag'

### What are the best alternatives to PDF & Office to Markdown for RAG?

The closest alternatives to PDF & Office to Markdown for RAG are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [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.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [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.
- [MedXpert 图书馆连接器（通用版）](https://ai-powered.com/mcp/medxpert): MedXpert 图书馆连接器（通用版） is an open-source MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/pdf-and-office-to-markdown-for-rag
