What it does
The server extracts text and tables from PDF documents and returns the document's metadata. It is intended for workflows that need content pulled out of PDF files rather than viewed or edited.
OCR support is provided for scanned documents, where the pages are images and contain no selectable text. The publisher's description does not list supported PDF features, output formats or setup steps beyond this.
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
io.github.sathvic-kollu/techtenstein-pdf
PDF text and table extraction plus metadata. Supports OCR for scanned documents.
v1.0.2As shown on registry.modelcontextprotocol.io when we last read it