Connect pdf.net to your ChatGPT or Claude (MCP)

pdf.net AI Assistant (MCP)

The pdf.net MCP connector lets you work with your documents directly inside Claude, ChatGPT, and other AI assistants — without switching tabs. Edit, generate, convert, merge, split, and organize PDFs through natural conversation.

What is the pdf.net MCP connector?

MCP (Model Context Protocol) is an open standard that lets AI assistants like Claude and ChatGPT connect to external tools and services. The pdf.net MCP connector gives your AI assistant direct access to your pdf.net library — so you can work with documents through conversation instead of clicking through a UI.

Once connected, you can say things like "merge these three contracts and compress the result" or "generate a payment invoice for Acme LLC" and your AI assistant will do it for you.

Which AI assistants are supported?

Any AI assistant that supports the MCP protocol, including:

Claude (claude.ai) — connect via Settings → Connectors
ChatGPT — connect via Settings → Connected apps

The connector is the same regardless of which assistant you use.

How do I connect pdf.net to my AI assistant?

In Claude: go to Settings → Connectors, search for "pdf.net", and click Connect. You'll be asked to sign in to your pdf.net account to authorize access.

In ChatGPT: go to Settings → Connected apps, find pdf.net, and follow the same authorization flow.

Once connected, the connector is available in every new conversation automatically.

Do I need a paid plan?

The MCP connector is available on all pdf.net plans, including free.

What can I ask my AI assistant to do with pdf.net?

Here's a full overview of what's available:

Capability	What it does
Upload & import	Upload files from your device or import from a URL. PDF, DOCX, XLSX, PPTX, PNG, JPG, and more — non-PDF formats are converted automatically.
Edit documents	Change text, add or remove pages, move paragraphs, reposition content — all directly inside the PDF without converting to Word first.
Generate documents	Create a new PDF from a plain-language description or fill in a template with specific details (client name, amount, date, etc.).
Convert	Export any document to DOCX, XLSX, PPTX, TXT, HTML, PNG, JPG, and more.
Merge	Combine up to 20 documents into one PDF in any order.
Split	Extract specific pages or page ranges as separate documents.
Compress	Reduce file size with three compression levels (low / medium / high).
Organize	Create folders, move, rename, copy, and delete documents and folders.
Download	Get a direct download link for any document in your library.

What are some useful things to try? What are some useful things to try?

What are some useful things to try?

Here are real workflows you can run with a single message to your AI assistant:

Generate a standard document

"Generate a payment invoice: Acme LLC, $15,000, software development services, March 2026."

Your assistant creates a ready-to-send PDF and gives you a download link — no templates, no manual formatting.

Fill a template for a specific client

"Here's my proposal template and the client details: client — Grand Pacific, contact — Sarah Chen, projected revenue — $42,000/mo, date — today. Fill in the template and send me the result."

The assistant copies your template, opens it for editing, replaces the placeholder fields, and returns a personalized document.

Batch-generate personalized proposals

"Here's my proposal template. Generate individual PDFs for each of these 10 clients: [paste table]. Name each file after the client and give me all the download links."

One message, ten personalized PDFs. The assistant runs the full workflow for each row and returns all links when done.

Prepare a deal package

"Merge the contract, Exhibit A, and the invoice into one PDF, update all dates to today, compress to the smallest size, and give me a download link."

Multi-step pipeline — merge, edit, compress — executed as a single conversation turn.

Edit contract details

"In the contract, replace 'Old Corp' with 'New Corp' everywhere and update the effective date to May 1, 2026."

The assistant reads the document structure, identifies the relevant paragraphs, and applies each change. No need to convert to Word.

Translate a document

"Translate this NDA from English to Spanish and give me a download link."

The assistant rewrites each paragraph in the target language directly inside the PDF, preserving the original layout and formatting.

Split a report into sections

"Split this 40-page report: pages 1–10 as the executive summary, 11–30 as the main body, 31–40 as appendices."

Produces three named files, each containing exactly the pages you specified.

Organize your library

"Create folders for Contracts, Invoices, and Reports. Move all files to the right folder by type."

The assistant lists your library, creates the folder structure, and moves each document to the correct location.

QA and Troubleshooting

Can my AI assistant edit text inside a PDF directly?

Yes. Unlike most tools that require you to convert a PDF to Word first, the pdf.net connector lets AI assistants edit text natively inside the PDF — keeping your original layout, fonts, and formatting intact.

The assistant opens an editor session, reads the document structure (pages, paragraphs, positions), and applies targeted changes paragraph by paragraph.

What kinds of edits are supported?

Replace or update text in any paragraph
Change text alignment, line height, or indentation
Add or remove pages
Move, duplicate, or reorder pages
Add, move, or remove text blocks
Bold, italic, superscript, subscript, and custom font styling per text run

How does document generation work?

Describe what you want in plain language and your AI assistant will create a complete, formatted PDF from scratch. You can specify:

Document type (invoice, NDA, proposal, report, etc.)
Key details (names, amounts, dates, clauses)
Language and tone
Structure and sections

The generated document is saved to your pdf.net library automatically, and your assistant provides a download link.

Generation takes a few seconds. Your assistant will let you know when it's ready.

Can I use my own template and fill in the details?

Yes — this is one of the most powerful workflows. Upload your template to pdf.net, then ask your assistant to copy it and fill in the specific details for each client or case. You can even provide a table of multiple clients and get personalized documents for each in one message.

Can my AI assistant access other users' documents?

No. Every tool in the connector is strictly scoped to your authenticated account. There is no way to access documents belonging to another user.

Are my documents safe when using the connector?

Yes. The same security standards that apply to pdf.net generally apply to the MCP connector:

All data is transmitted over TLS 1.2+
Documents are stored encrypted at rest (AES-256)
We do not sell your documents or their contents
We do not use your documents to train AI models

For full details, see File Security at pdf.net and our Data Processing Agreement.

Does authorizing the connector give my AI assistant access to everything?

The connector only has access to your pdf.net library — your documents and folders. It does not access your email, calendar, other connected apps, or anything outside pdf.net.

You can disconnect the connector at any time from your AI assistant's settings.

My AI assistant says it can't find a document

Try asking your assistant to list your library first: "Show me all my documents." This refreshes the document list and gives the assistant the current IDs. Then retry your original request.

I asked for a feature and the assistant opened the pdf.net website instead

Some features — like e-signing, annotations, form filling, and password protection — aren't available through the connector yet. When you ask for one of these, your assistant will give you a direct link to open the document in the pdf.net editor where you can complete the task.