Skip to content
Back to search

markdownify-mcp

A Model Context Protocol server for converting almost anything to Markdown

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/zcaceres--markdownify-mcp/badge.svg)](/listings/zcaceres--markdownify-mcp)

HTML

<a href="/listings/zcaceres--markdownify-mcp"><img src="/api/listings/zcaceres--markdownify-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Clone this repository 2. Install dependencies:

   bun install

The `preinstall` step creates a Python virtual environment at `.venv` and installs `markitdown[all]`.

3. Build the project:

   bun run build

4. Start the server:

   bun start

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 114 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Markdownify MCP Server
  2. ![markdownify mcp logo](logo.jpg)
  3. Markdownify is a Model Context Protocol (MCP) server that converts various file types and web content to Markdown format. It provides a set of tools to transform PDFs, images, audio files, web pages, and more into easily readable and shareable Markdown text.
  4. <a href="https://glama.ai/mcp/servers/bn5q4b0ett"><img width="380" height="200" src="https://glama.ai/mcp/servers/bn5q4b0ett/badge" alt="Markdownify Server MCP server" /></a>
  5. ## Features
  6. - Convert multiple file types to Markdown:
  7. - PDF
  8. - Images
  9. - Audio (with transcription)
  10. - DOCX
  11. - XLSX
  12. - PPTX
  13. - Convert web content to Markdown:
  14. - YouTube video transcripts
  15. - Bing search results
  16. - General web pages
  17. - Retrieve existing Markdown files
  18. ## Getting Started
  19. 1. Clone this repository
  20. 2. Install dependencies:
  21. ```
  22. bun install
  23. ```
  24. The `preinstall` step creates a Python virtual environment at `.venv` and installs `markitdown[all]`.
  25. 3. Build the project:
  26. ```
  27. bun run build
  28. ```
  29. 4. Start the server:
  30. ```
  31. bun start
  32. ```
  33. ## Development
  34. - Use `bun run dev` to start the TypeScript compiler in watch mode
  35. - Modify `src/server.ts` to customize server behavior
  36. - Add or modify tools in `src/tools.ts`
  37. ## Usage with Desktop App
  38. To integrate this server with a desktop app, add the following to your app's server configuration:
  39. ```js
  40. {
  41. "mcpServers": {
  42. "markdownify": {
  43. "command": "node",
  44. "args": [
  45. "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
  46. ]
  47. }
  48. }
  49. }
  50. ```
  51. ### Environment variables
  52. All paths default to sensible values; override only when the defaults don't fit your install layout.
  53. | Variable | Default | Purpose |
  54. |---|---|---|
  55. | `MARKITDOWN_PATH` | `<project>/.venv/bin/markitdown`, then `markitdown` on `PATH` | Absolute path to the `markitdown` executable. Set this when you've installed markitdown system-wide (e.g. `pipx install "markitdown[pdf]"`) instead of using the bundled venv. |
  56. | `REPOMIX_PATH` | `<project>/node_modules/.bin/repomix`, then `repomix` on `PATH` | Absolute path to the `repomix` executable used by `git-repo-to-markdown`. |
  57. | `MD_ALLOWED_PATHS` | unset (unrestricted) | Path-delimiter-separated list (`:` on POSIX, `;` on Windows) of directories the server is allowed to read. When set, all file-input tools (`pdf-to-markdown`, `get-markdown-file`, etc.) reject paths outside these directories. |
  58. | `MD_SHARE_DIR` | unset | Deprecated alias for `MD_ALLOWED_PATHS` (single directory). Still honored for backward compatibility. |
  59. ## Usage with Docker
  60. Build and run:
  61. ```sh
  62. docker build -t markdownify-mcp .
  63. docker run --rm -i \
  64. -v "$HOME/Documents:/data:ro" \
  65. -e MD_ALLOWED_PATHS=/data \
  66. markdownify-mcp
  67. ```
  68. Notes for the Docker MCP catalog (`mcp/markdownify`):
  69. - Mount any host directories you want the server to read into the container, then pass the **container** paths to the tools (e.g. `/data/foo.pdf`, not `/Users/you/Documents/foo.pdf`).
  70. - Set `MD_ALLOWED_PATHS` to the colon-separated list of mounted directories so the server enforces a read boundary that matches the bind mount.
  71. - The published Docker image installs `markitdown[pdf]` only — audio transcription and image OCR (`audio-to-markdown`, `image-to-markdown`) require the `[all]` extras and will fail in the slim image. Use the local install (`bun install`) for the full feature set.
  72. ## Available Tools
  73. - `youtube-to-markdown`: Convert YouTube videos to Markdown
  74. - `pdf-to-markdown`: Convert PDF files to Markdown
  75. - `bing-search-to-markdown`: Convert Bing search results to Markdown
  76. - `webpage-to-markdown`: Convert web pages to Markdown
  77. - `image-to-markdown`: Convert images to Markdown with metadata
  78. - `audio-to-markdown`: Convert audio files to Markdown with transcription
  79. - `docx-to-markdown`: Convert DOCX files to Markdown
  80. - `xlsx-to-markdown`: Convert XLSX files to Markdown
  81. - `pptx-to-markdown`: Convert PPTX files to Markdown
  82. - `get-markdown-file`: Retrieve an existing Markdown file. File extension must end with: *.md, *.markdown.
  83. OPTIONAL: set `MD_ALLOWED_PATHS` to restrict every file-input tool to a list of directories, e.g. `MD_ALLOWED_PATHS=/data/in:/data/out bun start`.
  84. ## Contributing
  85. Contributions are welcome! Please feel free to submit a Pull Request.
  86. ## License
  87. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.