Doc To Markdown MCP Server avatar
Doc To Markdown MCP Server

Pricing

Pay per event

Go to Apify Store
Doc To Markdown MCP Server

Doc To Markdown MCP Server

An MCP server that converts documents to clean Markdown. Convert PDFs, Word docs, Excel spreadsheets, PowerPoints, HTML, images, and more to AI-friendly Markdown format.

Pricing

Pay per event

Rating

0.0

(0)

Developer

AbotAPI

AbotAPI

Maintained by Community

Actor stats

0

Bookmarked

1

Total users

0

Monthly active users

4 days ago

Last modified

Share

Document to Markdown MCP Server

An Apify MCP server that converts documents to clean Markdown. Convert PDFs, Word docs, Excel spreadsheets, PowerPoints, HTML, images, and more to AI-friendly Markdown format.

About this MCP Server

To understand how to connect to and utilize this MCP server, please refer to the official Model Context Protocol documentation at mcp.apify.com.

Connection URL

MCP clients can connect to this server at:

https://actors-mcp-server--doc-to-markdown-mcp.apify.actor/mcp

Standby Mode

This Actor uses Standby mode, a new, lightweight method for using Actors. Instead of starting an Actor for each input and waiting for results, the Actor remains ready in the background to handle arbitrary HTTP requests, just like any web or API server. Learn more.

This is a new feature, and we'd love to hear your feedback.

Actor URL

Send an HTTP request to this URL, and wait for the response:

https://actors-mcp-server--doc-to-markdown-mcp.apify.actor?token=YOUR_APIFY_TOKEN

The MCP endpoint is available at /mcp:

https://actors-mcp-server--doc-to-markdown-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN

Key Features

  • Batch Processing: Handle up to 20 documents simultaneously for increased productivity
  • Extensive Format Support: Convert 15+ file formats with intelligent content extraction
  • Customizable Output: Tailor markdown formatting to meet specific needs
  • MCP Integration: Compatible with MCP-compatible AI systems and chatbots
  • Metadata Preservation: Maintain essential document metadata during conversion
  • Table and Image Handling: Recognize table structures and manage images effectively

Supported Formats (15+)

CategoryFormats
DocumentsPDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), RTF
WebHTML, XML
ImagesJPEG, PNG, GIF, BMP (with EXIF metadata extraction)
AudioWAV, MP3 (with speech transcription)
DataCSV, JSON, YAML
ArchivesZIP (recursive extraction)

MCP Tools

Single Document Conversion

convert_url_to_markdown

Convert a document from a URL to Markdown.

{
"url": "https://example.com/document.pdf",
"options": {
"include_metadata": true,
"include_toc": true
}
}

convert_file_to_markdown

Convert a file from Apify Key-Value Store.

{
"key": "my-document.pdf",
"options": {
"include_metadata": true
}
}

convert_base64_to_markdown

Convert a base64-encoded document.

{
"content": "base64-encoded-content",
"filename": "document.pdf"
}

convert_html_to_markdown

Convert HTML content directly.

{
"html": "<h1>Hello World</h1><p>Content here</p>"
}

Batch Processing

batch_convert_urls

Convert multiple documents from URLs simultaneously (max 20).

{
"urls": [
"https://example.com/doc1.pdf",
"https://example.com/doc2.docx",
"https://example.com/doc3.pptx"
],
"options": {
"include_metadata": true
}
}

batch_convert_files

Convert multiple files from Key-Value Store (max 20).

{
"keys": ["report1.pdf", "report2.docx", "data.xlsx"]
}

Utility Tools

extract_metadata

Extract metadata without full conversion.

{
"url": "https://example.com/document.pdf"
}

get_supported_formats

List all supported file formats.

get_output_options

Get available formatting options.

Output Formatting Options

Customize your markdown output with these options:

OptionTypeDefaultDescription
include_metadatabooleantrueInclude file metadata header
include_tocbooleanfalseGenerate table of contents
heading_stylestring"atx""atx" (# Heading) or "setext" (underlined)
table_formatstring"pipe""pipe" (|col|) or "simple"
image_handlingstring"reference""inline", "reference", or "extract"

Example with Options

{
"url": "https://example.com/report.pdf",
"options": {
"include_metadata": true,
"include_toc": true,
"heading_style": "atx",
"table_format": "pipe"
}
}

Usage

With Claude Desktop

Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json):

{
"mcpServers": {
"doc-to-markdown": {
"url": "https://actors-mcp-server--doc-to-markdown-mcp.apify.actor/mcp",
"headers": {
"Authorization": "Bearer YOUR_APIFY_TOKEN"
}
}
}
}

Uploading Files to Key-Value Store

Via Apify Console

  1. Go to Actor's StorageKey-Value Store
  2. Click Add record
  3. Upload your file
  4. Use the key name in convert_file_to_markdown

Via API

curl -X PUT \
"https://api.apify.com/v2/key-value-stores/YOUR_STORE_ID/records/document.pdf" \
-H "Authorization: Bearer YOUR_APIFY_TOKEN" \
-H "Content-Type: application/pdf" \
--data-binary @document.pdf