document-parser
Verified · todayParse and extract structured data from various document formats (PDF, Word, HTML).
Install
claude mcp add document-parser -- npx -y @agenson-horrowitz/[email protected]
Our take
Local document-parsing MCP server for PDFs, OCR on images, HTML-to-Markdown, table extraction, and document summaries. The tool surface is straightforward and implemented in the repo, with heavy dependencies such as Tesseract, Sharp, and PDF parsers that users should expect to install and maintain. The young org has several agent-focused sibling projects, but this package's downloads sit at normal mirror baseline rather than looking inflated.
Verification record
- today
- 0
- 3 mo ago
- no
- MIT
- 193
- 1.0.8
- 2026-04-02