# Tools

> Every listed resource, editors’ picks first. The filters below can be combined.

- Search: append `?q=<keywords>` to the URL. Separate several keywords with spaces; all of them must match. Matches name, repository, tags, professions, description and README.
- Filter by type: append `?type=<cli|skill|plugin|mcp>` to the URL.
- Filter by profession: append `?profession=<profession id>` to the URL. Separate several ids with commas; a resource matches when it suits any of them. Ids are listed at https://hebbmind.com/api/v1/professions
- Filter by tag: append `?tag=<tag>` to the URL. Separate several tags with commas; a resource must carry all of them. Tags are listed at https://hebbmind.com/api/v1/tags

Resources for ML / AI, Tagged `pdf`, `python`: 7 items.

> Model training, evaluation and LLM application development.

- [MarkItDown-MCP](https://hebbmind.com/ja/mcp/markitdown-mcp.md): [MCP] From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.
- [MarkItDown](https://hebbmind.com/ja/cli/markitdown.md): [CLI] Converts PDF, Word, Excel, PowerPoint, HTML, images, audio and more into Markdown that keeps headings, lists and tables, ready for LLMs to read and analyze. Maintained by Microsoft; requires Python 3.10+.
- [PaddleOCR MCP Server](https://hebbmind.com/ja/mcp/paddlepaddle-mcp-server.md): [MCP] Official PaddleOCR MCP: text recognition and layout parsing for images and PDFs (PP-OCR, PP-StructureV3, PaddleOCR-VL), returning text or Markdown. Runs inference locally, or calls the official API or a self-hosted service.
- [Docling](https://hebbmind.com/ja/cli/docling.md): [CLI] Parses PDF, DOCX, PPTX, XLSX, HTML, images and audio, recovering layout, reading order, tables and formulas, and exports Markdown, HTML or lossless JSON. Started by IBM Research, now hosted by the LF AI & Data Foundation; runs fully locally.
- [Marker](https://hebbmind.com/ja/cli/marker.md): [CLI] Converts PDFs, images, PPTX, DOCX, XLSX, EPUB and more into Markdown, JSON or HTML, preserving tables, formulas and layout, with optional LLM help for higher accuracy. Needs Python 3.10+ and PyTorch; large-scale commercial use of the model weights needs a paid license.
- [Paper Search MCP](https://hebbmind.com/ja/mcp/paper-search-mcp.md): [MCP] Unified search across 20+ academic sources including arXiv, PubMed, bioRxiv, Semantic Scholar and OpenAlex, returning deduplicated, normalized results and downloading full text via open-access channels first. Most sources need no API key.
- [MinerU Open MCP](https://hebbmind.com/ja/mcp/opendatalab-mcp.md): [MCP] MinerU's official MCP: parses PDF, Word, PowerPoint and images into Markdown via the mineru.net cloud API, keeping tables and formulas. The keyless Flash mode works out of the box; add a token for higher quotas and more formats.