pdf_oxide
yfedoseev/pdf_oxide
PDFOxide is an ultra-fast, specification-compliant PDF processing toolkit built in Rust with multi-language bindings and an MCP server for AI assistants.
Overview
PDFOxide provides high-performance text extraction, image extraction, and markdown conversion capabilities based on a robust Rust core. Featuring bindings for 20 programming languages alongside a command-line interface and Model Context Protocol (MCP) server, it is designed for speed, low latency, and accurate parsing of complex PDF documents without sacrificing extraction quality.
Capabilities
- ▸High-speed text and layout extraction
- ▸Image and vector graphics extraction
- ▸Markdown and HTML conversion
- ▸Scoped region extraction
- ▸Form field reading and writing
- ▸MCP server integration for AI assistants
- ▸Multi-language binding support
Best for
Extracting text, images, and layout structures from PDF documents inside AI pipelines or applications., Converting dense PDF documents into structured markdown for retrieval-augmented generation (RAG) or analysis., Reading and editing PDF form fields, annotations, and bookmarks programmatically., Enabling LLMs and AI coding agents to search, read, and inspect PDF files via an MCP server.
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
The skill operates locally on PDF files provided by the user. Standard safety precautions for handling untrusted file inputs apply to prevent potential parser exploits in native code libraries.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.