What it does
PennyOCR is an MCP server published by imiraoui. It reads PDF files and images and returns their content as markdown or text. The publisher states that it reports exact costs and enforces hard spend caps, priced at $0.75 per 1,000 pages.
It suits workflows where text from scanned documents or images needs to be extracted for use in an AI client, particularly where per-page cost and spending limits need to be controlled.
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
com.pennyocr/ocr
Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it