Word to Markdown MCP
The Word to Markdown MCP server: an agent turns a .docx file into clean Markdown locally, with images, tables and footnotes.
- 272 ★ on the repository
- Last commit
- Apache-2.0
Minimal access
Why this level
- Reads `.docx` files at the given path and, when asked, writes `.md` and image files to disk.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/word-to-markdown-mcpDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- Reads `.docx` files at the given path and, when asked, writes `.md` and image files to disk.
This is third-party code. Review the repository files before installing.
What it does
Word to Markdown is a Word-to-Markdown document converter: a command-line tool, a Node.js library and the word2md.com page in the browser. The `w2m mcp` command starts a local MCP server over stdio, so the agent converts `.docx` on your machine and nothing is uploaded. The agent passes a file path, and the server reads it and returns Markdown and warnings about losses. The server has one tool, `convert_docx_to_markdown`. The `path` parameter is required, `output_path` writes the result to a `.md` file for long documents, `image_dir` extracts images into a folder and links them, `overwrite` allows replacing files, and `bullet_lists` and `preserve_footnotes` repeat the tool flags. The converter handles headings, lists, tables, links, footnotes and equations, which it turns into LaTeX.
Who it is for. Documentation authors and analysts who move reports and policies from Word into a repository or into an agent context.
Good fit when
- A policy in .docx has to become Markdown and go into a documentation repository.
- An agent reads a long report and the result is written straight to a file to keep the context light.
- Images from a document are extracted to a folder and linked with relative paths.
- Office Math equations are needed as LaTeX for rendering on GitHub.
Not a fit when
- You need legacy `.doc` files or other formats, while the tool accepts only `.docx`.
- Comments, headers and footers and underlining matter, and by default they are dropped.
- A document from an untrusted source may contain hidden instructions for the agent.
Example request
Convert /Users/me/docs/policy.docx to Markdown, extract images into an images folder and save the result next to it as policy.md.MCP
- Transport
- stdio
- Authentication
- not required
Limitations
Only `.docx` files are accepted. Comments, headers, footers and underlining are dropped by default, and warnings report the losses. Text boxes without a VML fallback disappear. Quotes are normalised to ASCII except in mostly Chinese text. Images are dropped by default: base64 would flood the agent context. The `overwrite` parameter is off, so the tool does not clobber files on instructions found in a document. The library needs Node.js 22.13 or newer.
How to disable. Remove the word-to-markdown entry from the MCP configuration (`claude mcp remove word-to-markdown`). The Claude Desktop extension is removed in the extension settings.
FAQ
How do I connect Word to Markdown to Claude Code?
Run `claude mcp add word-to-markdown -- npx -y word-to-markdown mcp`. For other clients add an `mcpServers` entry with the command `npx` and the arguments `-y word-to-markdown mcp`.
Is Node.js needed for Claude Desktop?
No. The `word-to-markdown.mcpb` file installs by double click as an extension and brings its own runtime.
What does the `image_dir` parameter do?
It extracts images into the given folder and links them. The folder must be relative and sit inside the `output_path` folder or the `.docx` folder.
Does the document go to the internet?
No. The server runs locally, the agent passes a file path, and the word2md.com site does not upload documents either.
How do I convert from the console?
Run `npx word-to-markdown input.docx > output.md`. Add `--bullet-lists` for numbered lists as bullets and `--image-dir <folder>` to extract images to files.
Discussion
No questions or reviews yet.
Related
MCP serversAn MCP server that turns PDF, DOCX, XLSX, PPTX, images, audio, web pages and YouTube transcripts into Markdown
Microsoft's utility and MCP server that turn PDF, Word, Excel, PowerPoint, HTML and other files into Markdown for models
MCP Word server for docx editing with tracked changes: comments, footnotes, version comparison and a change log, all visible in Word
Word MCP Live
word-mcp-live
An MCP server for Microsoft Word: the agent edits an open document live, with tracked changes, comments and action rollback
Adeu: an MCP server, skill and CLI for editing .docx through an agent with real Track Changes, comments and version diffs.
Doc-Ops MCP converts DOCX, Markdown, HTML and PDF between formats and stamps a watermark or QR code onto finished PDFs.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Word to Markdown MCP (this card) | yes | not required | 272 | |
| MarkItDown | yes | not required | 195,008 | converts PDF, Word, Excel and other formats to Markdown; Word to Markdown focuses on .docx and extracts images and equations |
| mcp-pandoc | no | not required | 587 | converts documents between many formats through pandoc; Word to Markdown works without pandoc on Mammoth |
README in short
The converter is built on Mammoth and produces GitHub-flavoured Markdown. It is available as a command-line tool, an ES module library with TypeScript types, an MCP server and a browser page.