What it does
The server converts PDF, Word, PPT and HTML documents to Markdown. Tables are returned as JSON, and images can be extracted from the documents.
It fits workflows that need document content as text, or as chunks for retrieval-augmented generation (RAG). Processing can be limited to specific page ranges.
The publisher description does not list installation or configuration steps.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
stagenth · 文档解析
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it