# Document to Markdown for LLM & RAG

> Document to Markdown for LLM & RAG is a paid MCP server for files and documents. Converts PDFs, Office files and scans to Markdown or RAG chunks, priced 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://tidewellsoftware.com/doc-to-markdown/
- **MCP Registry name:** com.tidewellsoftware/doc-to-markdown
- **Categories:** files and documents, knowledge and memory, AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

Headings are rebuilt from font sizes and weights, lists stay lists, tables become Markdown tables and running headers, footers and page numbers are dropped. Pages with a text layer are read directly; Tesseract OCR runs only on scanned pages and images, in 25 languages.

Output is either one Markdown file per document or JSON chunks split by heading or by token count (default 512 with 64 overlap), each carrying page_start, page_end, heading_path and a token count. Input can be file URLs, uploaded files, key-value store entries or a dataset of links from another crawler, and Google Drive, Dropbox and GitHub share links are converted to direct downloads. Slides become one page each with speaker notes; spreadsheets become one table per sheet.

It runs as an Apify Actor behind a hosted MCP endpoint. Only pages that produced text are billed; failed, encrypted and empty files are free.

## Features

- **Heading-aware Markdown:** Reconstructs headings, lists and tables from PDF layout and Office structure.
- **Built-in OCR:** Reads scanned pages and images with Tesseract in 25 languages.
- **RAG chunks:** Splits by heading or token count with page range and heading path metadata.
- **Many formats:** PDF, DOCX, PPTX, XLSX, HTML, EPUB, CSV and common image formats.
- **Image extraction:** Can save embedded images to a key-value store and link them from the Markdown.
- **Page markers:** Optionally inserts page comments so answers can cite page numbers.

## Good for

- Build a RAG knowledge base from manuals and contracts
- Turn scanned invoices or letters into searchable text
- Load slide decks and spreadsheets into a vector store
- Convert pages found by a crawler into Markdown for an agent

## Install

### Claude Code (Terminal)

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

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

```sh
https://mcp.apify.com/?tools=tidewell/doc-to-markdown
```

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

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

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

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

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

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

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

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

## FAQ

### Is OCR always on?

OCR is on by default but runs only on pages without a text layer; forceOcr overrides that.

### Can it open password-protected PDFs?

Yes, through the pdfPassword option; encrypted files without a password fail and are not charged.

### What size limits apply?

Defaults are 100 MB per file, 300 seconds per document and three concurrent conversions.

### Is Document to Markdown for LLM & RAG free?

No. Document to Markdown for LLM & RAG is a paid product.

### How do I add Document to Markdown for LLM & RAG to Claude Code?

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

### What are the best alternatives to Document to Markdown for LLM & RAG?

The closest alternatives to Document to Markdown for LLM & 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/document-to-markdown-for-llm-and-rag
