oxidize-pdf MCP server

This is a helper for your AI that works with PDF files. It comes from a Python library called oxidize-pdf, and it includes a small server that your AI can talk to. It is handy if you deal with PDFs all day: reports, invoices, contracts, scanned forms, and you want your AI to open them, pull out the text, or make new ones for you.

What this MCP server does

You point the helper at a folder of PDFs on your computer. Then you ask your AI something in plain words, like how many pages a file has or what it says. The AI passes your request to this helper, the helper opens the PDF, and sends the answer back. For changes, the helper can split, merge, rotate, annotate, or fill forms, and save the result as a new file in that same folder. You see the result in the chat as text, a short summary, or a note that a new file was saved.

Click to zoom

What you can do with it

• Read a PDF and tell you how many pages it has, plus the title and author
• Pull the text out of a PDF so you can search it or feed it to your AI
• Turn a PDF into Markdown or plain chunks that are easier for AI to read
• Split a big PDF into single pages, or merge several PDFs into one
• Rotate pages or pull out just the pages you want
• Add text notes and highlights to a PDF
• Fill in form fields on a PDF and save the result
• Create a brand new PDF with text and simple shapes

Try asking your AI

• “How many pages does report.pdf have, and who wrote it?”
• “Extract all the text from invoice.pdf and give me a short summary.”
• “Merge part1.pdf and part2.pdf into one file called combined.pdf.”
• “Convert contract.pdf to Markdown so I can paste it into my notes.”

What it gives back to you

You get answers in the chat: page counts, titles, authors, encryption status, and the text of the pages you asked for. For conversions, you get Markdown or text chunks you can copy. For changes, the helper saves a new PDF in your workspace folder and tells you the file name. It can also list the PDFs it can see in that folder.

Before you start

Who it's for

Anyone who works with PDFs often, like office admins, accountants, lawyers, researchers, and support staff who want their AI to read or tidy up documents for them.