What it does
Rosetta PDF is an MCP server that lets Cursor and Claude work with digital PDF files. According to the publisher, it can parse documents, extract their content, split them, and answer questions over them. It works on PDFs that have a text layer and does not perform OCR, so scanned pages without embedded text are outside its stated scope.
It is suited to tasks where an assistant needs to read or query the text of a PDF from inside an editor or chat client, such as pulling content out of a document or working through its sections.
The publisher's description does not give details on setup beyond connecting it as an MCP server to Cursor or Claude.
Limitations and requirements
Works only on digital PDFs with a text layer; no OCR is performed, so scanned documents without text are not covered.
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
Rosetta PDF
Parse, extract, split, and ask over digital PDFs (text layer, no OCR) from Cursor and Claude.
v0.2.2As shown on registry.modelcontextprotocol.io when we last read it