What it does
This MCP server, published by filegraph, extracts text from documents, lets an AI client manipulate PDF files, and runs optical character recognition (OCR) on images. It is listed as an MCP resource in the documents and design-media categories.
It suits work where document contents need to be read or changed by an assistant: pulling text out of files, editing PDFs, or turning scanned images into machine-readable text. The publisher's description covers these three functions; no further operations are listed in the facts provided.
The source repository is available on GitHub at the listed URL. Setup details, supported file formats and runtime requirements are not included in the facts provided, so they are not described here.
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
ai.filegraph/document-processing
Extract text from documents, manipulate PDFs, and perform OCR on images.
v1.0.1As shown on registry.modelcontextprotocol.io when we last read it