[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73821":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":14,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":35,"readmeContent":36,"aiSummary":37,"trendingCount":16,"starSnapshotCount":16,"syncStatus":38,"lastSyncTime":39,"discoverSource":40},73821,"markdownify-mcp","zcaceres\u002Fmarkdownify-mcp","zcaceres","A Model Context Protocol server for converting almost anything to Markdown","",null,"TypeScript",2729,229,9,8,0,3,16,56,29.09,"MIT License",false,"main",true,[26,27,28,29,30,31,32,33,34],"ai","anthropic","anthropic-ai","anthropic-claude","markdown","mcp","model-context-protocol","ocr","tools","2026-06-12 02:03:18","# Markdownify MCP Server\n\n![markdownify mcp logo](logo.jpg)\n\nMarkdownify 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.\n\n\u003Ca href=\"https:\u002F\u002Fglama.ai\u002Fmcp\u002Fservers\u002Fbn5q4b0ett\">\u003Cimg width=\"380\" height=\"200\" src=\"https:\u002F\u002Fglama.ai\u002Fmcp\u002Fservers\u002Fbn5q4b0ett\u002Fbadge\" alt=\"Markdownify Server MCP server\" \u002F>\u003C\u002Fa>\n\n## Features\n\n- Convert multiple file types to Markdown:\n  - PDF\n  - Images\n  - Audio (with transcription)\n  - DOCX\n  - XLSX\n  - PPTX\n- Convert web content to Markdown:\n  - YouTube video transcripts\n  - Bing search results\n  - General web pages\n- Retrieve existing Markdown files\n\n## Getting Started\n\n1. Clone this repository\n2. Install dependencies:\n   ```\n   bun install\n   ```\n\n   The `preinstall` step creates a Python virtual environment at `.venv` and installs `markitdown[all]`.\n\n3. Build the project:\n   ```\n   bun run build\n   ```\n4. Start the server:\n   ```\n   bun start\n   ```\n\n## Development\n\n- Use `bun run dev` to start the TypeScript compiler in watch mode\n- Modify `src\u002Fserver.ts` to customize server behavior\n- Add or modify tools in `src\u002Ftools.ts`\n\n## Usage with Desktop App\n\nTo integrate this server with a desktop app, add the following to your app's server configuration:\n\n```js\n{\n  \"mcpServers\": {\n    \"markdownify\": {\n      \"command\": \"node\",\n      \"args\": [\n        \"{ABSOLUTE PATH TO FILE HERE}\u002Fdist\u002Findex.js\"\n      ]\n    }\n  }\n}\n```\n\n### Environment variables\n\nAll paths default to sensible values; override only when the defaults don't fit your install layout.\n\n| Variable | Default | Purpose |\n|---|---|---|\n| `MARKITDOWN_PATH` | `\u003Cproject>\u002F.venv\u002Fbin\u002Fmarkitdown`, 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. |\n| `REPOMIX_PATH` | `\u003Cproject>\u002Fnode_modules\u002F.bin\u002Frepomix`, then `repomix` on `PATH` | Absolute path to the `repomix` executable used by `git-repo-to-markdown`. |\n| `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. |\n| `MD_SHARE_DIR` | unset | Deprecated alias for `MD_ALLOWED_PATHS` (single directory). Still honored for backward compatibility. |\n\n## Usage with Docker\n\nBuild and run:\n```sh\ndocker build -t markdownify-mcp .\ndocker run --rm -i \\\n  -v \"$HOME\u002FDocuments:\u002Fdata:ro\" \\\n  -e MD_ALLOWED_PATHS=\u002Fdata \\\n  markdownify-mcp\n```\n\nNotes for the Docker MCP catalog (`mcp\u002Fmarkdownify`):\n- Mount any host directories you want the server to read into the container, then pass the **container** paths to the tools (e.g. `\u002Fdata\u002Ffoo.pdf`, not `\u002FUsers\u002Fyou\u002FDocuments\u002Ffoo.pdf`).\n- Set `MD_ALLOWED_PATHS` to the colon-separated list of mounted directories so the server enforces a read boundary that matches the bind mount.\n- 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.\n\n## Available Tools\n\n- `youtube-to-markdown`: Convert YouTube videos to Markdown\n- `pdf-to-markdown`: Convert PDF files to Markdown\n- `bing-search-to-markdown`: Convert Bing search results to Markdown\n- `webpage-to-markdown`: Convert web pages to Markdown\n- `image-to-markdown`: Convert images to Markdown with metadata\n- `audio-to-markdown`: Convert audio files to Markdown with transcription\n- `docx-to-markdown`: Convert DOCX files to Markdown\n- `xlsx-to-markdown`: Convert XLSX files to Markdown\n- `pptx-to-markdown`: Convert PPTX files to Markdown\n- `get-markdown-file`: Retrieve an existing Markdown file. File extension must end with: *.md, *.markdown.\n\n  OPTIONAL: set `MD_ALLOWED_PATHS` to restrict every file-input tool to a list of directories, e.g. `MD_ALLOWED_PATHS=\u002Fdata\u002Fin:\u002Fdata\u002Fout bun start`.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n","Markdownify MCP 是一个用于将多种文件类型和网页内容转换为 Markdown 格式的服务器。它支持 PDF、图片、音频文件（带转录）、DOCX、XLSX、PPTX 等多种格式的转换，并且可以处理 YouTube 视频字幕、Bing 搜索结果和普通网页内容。项目使用 TypeScript 编写，具备良好的扩展性和定制性。适用于需要将不同格式的内容统一转化为 Markdown 的场景，如文档管理、知识库构建等。",2,"2026-06-11 03:47:31","high_star"]