OpenReader is a free PDF reader for your computer. Read files, highlight stuff, search for words, compare two documents, and pick up where you left off. Your files stay on your computer. No one sees them. Not even us.
Open OpenReader, open a PDF, and everything you need is right there. Read, highlight, search, compare—all in one clean window. No tabs. No toolbars. No noise.
Your files never leave your computer. There’s no cloud, no tracking, no sign-up. It’s built for people who want a tool that just works and doesn’t ask for anything in return.
Just the stuff you actually need to do with PDFs—without a subscription or a browser eating your RAM.
Highlight, underline, cross out, and add notes on any page. Copy text with formatting. Everything stays on your computer.
Search for any word across your open document. Results show up instantly. No waiting, no loading bars.
See exactly what changed between two versions—word by word, page by page. Great for contracts or draft reviews.
Close the app, open it later, and all your documents and highlights are still there. Nothing lost.
No internet needed. No account. No cloud uploads. The file never leaves your machine. Ever.
Native Windows app (Microsoft Store). Experimental on Mac. Built with Python. Free and open source.
OpenReader has a built-in MCP server that lets AI assistants like Claude, ChatGPT, and Cursor open and work with your PDFs. Ask your AI to "find the contract clause about refunds" or "compare these two PDFs and tell me what changed"—the AI reads the files on your computer locally, so nothing is ever uploaded.
Run this in your terminal — only need to do it once:
pip install openreader-mcp
Copy the prompt below and paste it into your AI chat. The AI will know how to connect to your PDFs.
You now have access to the OpenReader MCP server, which lets you read, search, compare, and manage PDF files on my local computer. Here is how to set up the MCP server for your environment:{ "mcpServers": { "openreader": { "command": "python", "args": ["-m", "openreader_mcp"] } } }I installed it withpip install openreader-mcp. My PDFs are on my local filesystem — ask me for file paths when you need to open one. Available tools: -extract_text— read all text from a PDF -get_page_text— read one specific page -get_metadata— get document info (page count, author, title) -search_pdf— find a word or phrase inside a PDF -compare_pdfs— show differences between two PDFs -merge_pdfs— combine multiple PDFs into one file -split_pdf— split a PDF into separate pages -extract_pages— pull out specific pages from a PDF -compress_pdf— make a PDF file smaller -index_folder— build a searchable index of all PDFs in a folder -search_library— search across all indexed PDFs at once -search_semantic— meaning-based search across indexed PDFs -list_indexed_docs— list all PDFs currently in the search index
14 tools. All local. No data ever leaves your machine. Full setup guide
Download from the Microsoft Store or build from source on GitHub. No sign-up, no subscription—just a tool that respects your privacy.