ChatGPT + pdfmcp: setup guide

Connect pdfmcp to ChatGPT as a developer-mode MCP connector.

What you need: a free pdfmcp API key — sign in with your email (no password) and copy the key shown at first login. Then replace pdfmcp_live_YOUR_KEY in the config below.

Where it goes: ChatGPT → Settings → Connectors → Advanced (Developer mode)

Name:  pdfmcp
URL:   https://mcp.pdfmcp.org/mcp

Steps

  1. Get a free API key from the pdfmcp dashboard.
  2. In ChatGPT, open Settings → Connectors → Advanced and turn on Developer mode.
  3. Back in Connectors, choose “Create”, name it “pdfmcp” and paste the server URL above.
  4. If the form offers an authentication or header field, enter your key as “Bearer pdfmcp_live_YOUR_KEY”.
  5. In a new chat, enable the pdfmcp connector from the tools menu and ask it to work on a PDF.

ChatGPT's connector UI changes often and some plans authenticate connectors with OAuth only. If your form has no place for an API-key header, ChatGPT can't attach the key yet — every other client on this page can, and the same key also works directly against the REST API.

Troubleshooting

Try it with

On-devicePDF to textExtract plain text, one form-feed separated section per page.On-deviceCompress PDFReduce file size with Ghostscript. Presets: light (printer quality), medium (ebook), heavy (screen, smallest).API · MCPOCR — searchable PDFMake a scanned PDF searchable: pages without a text layer are OCR'd with Tesseract and gain an invisible text layer; pages that already have text are passed through and reported as skipped.

More clients: Claude Desktop MCP setup · Claude Code MCP setup · Cursor MCP setup · All MCP setup guides · REST API quickstart