THE IDEA
Here’s what you need to know.
Microsoft's MarkItDown converts PDFs, Word documents, spreadsheets, presentations, web pages, images, audio, ZIP files, and YouTube URLs into structured Markdown. That can remove layout overhead and give an AI a cleaner text-first input, but the saving depends on the file. Keep the original PDF when its charts, images, handwriting, or page layout carry meaning.
See the visual breakdown
- 1
Choose a text-heavy file
- 2
Convert with MarkItDown
- 3
Check the .md output
- 4
Upload it to Claude
- 5
Ask with section citations
Markdown
Best for clean text, headings, lists, links, and straightforward tables.
Original PDF
Best when charts, images, handwriting, or exact layout matter.
Both
Use both when you want efficient text analysis plus visual verification.
MCP
Useful for repeat conversion, but it must be configured, invoked, and tightly scoped.
11 of 11 items
Everything you need
- Open
Microsoft MarkItDown
The official repository, supported formats, installation instructions, command-line examples, and security notes.
- Open
Official MarkItDown MCP guide
Microsoft's installation, Docker, Claude Desktop configuration, usage, and security guidance for markitdown-mcp.
- Open
Claude file-upload guide
Anthropic's current supported file types, limits, PDF processing behaviour, and advice for large documents.
What MarkItDown can convert
PDF
Text and document structure
Word
DOCX document content
Excel
Spreadsheet values and tables
PowerPoint
Slide text and structure
Images
Metadata and OCR when configured
Audio
Metadata and transcription when configured
Web formats
HTML, CSV, JSON, XML, and more
Other sources
ZIP files, EPUBs, and YouTube URLs
PUT IT INTO PRACTICE
Follow the steps.
Tick off each step as you go. Your progress is saved on this browser.
- STEP 01
Use MarkItDown for text-heavy reports, articles, policies, transcripts, Word files, slide text, and straightforward tables. Upload the original PDF when you need Claude to inspect diagrams, charts, photos, handwriting, or the exact page layout. Claude analyses both text and visual elements in PDFs of 100 pages or fewer, so converting everything is not always better.
- STEP 02
MarkItDown requires Python 3.10 or newer. Microsoft's repository recommends using a virtual environment. Install the complete converter with: pip install 'markitdown[all]'. Download and install only from the official Microsoft repository or Python package instructions linked below.
- STEP 03
Run: markitdown input.pdf -o output.md. Replace the filenames with your real input and output paths. Open the resulting Markdown file and quickly check headings, tables, page order, and missing text before relying on it.
- STEP 04
Attach the checked .md file and tell Claude what outcome you need. Markdown is close to plain text while retaining headings, lists, tables, and links, which makes it well suited to text analysis. Token savings vary, so compare the context or usage shown by your AI tool rather than assuming a fixed percentage.
Use the attached Markdown document as the source of truth. First map its headings and main sections, then answer my question with concise citations to the relevant heading or quoted passage. Flag any broken tables, missing context, image references, or formatting that may have been lost during conversion. MY QUESTION: [Write your question here]
- STEP 05
Microsoft also maintains markitdown-mcp for local MCP clients such as Claude Desktop. The official instructions recommend Docker and show how to add the server to claude_desktop_config.json. The server exposes a convert_to_markdown tool; it does not automatically intercept every ordinary file upload. You or Claude must call the tool, and its returned Markdown still enters the conversation context.
- STEP 06
The MCP server runs with your local user permissions and can read files that process can access. Use Microsoft's Docker setup, mount only the folder you intend to convert, keep the server bound to localhost, and never expose it to the public internet without proper security controls.
A FEW THINGS THAT HELP
Get more out of it.
- The tool is called MarkItDown, not Markdown. Markdown is the output format.
- There is no official universal 70% token-saving guarantee. The result depends on the original file and what the conversion keeps.
- Do not discard the original document. Markdown conversion can lose visual context, layout, annotations, and complex table structure.
- Scanned PDFs may need OCR and a manual accuracy check before the Markdown is trustworthy.
- The MCP tool returns converted content to the client, so very large Markdown output can still consume context.
- Only convert documents you are allowed to process, and avoid giving a local MCP server broader file access than it needs.