REST API quickstart + pdfmcp: setup guide

Submit a job, poll for it, download the result — the whole REST API in three calls.

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: Any HTTP client

# 1) submit a job (asynchronous — you get a job id)
curl -X POST https://api.pdfmcp.org/v1/jobs \
  -H "X-API-Key: pdfmcp_live_YOUR_KEY" \
  -F [email protected] -F op=compress -F preset=medium

# 2) poll until status is "completed"
curl https://api.pdfmcp.org/v1/jobs/JOB_ID -H "X-API-Key: pdfmcp_live_YOUR_KEY"

# 3) download the result (available for 1 hour)
curl https://api.pdfmcp.org/v1/jobs/JOB_ID/result -H "X-API-Key: pdfmcp_live_YOUR_KEY" -o report-compressed.pdf

Steps

Get a free API key from the pdfmcp dashboard (email sign-in, no password).
Submit jobs as multipart form posts: one or more files in the field “files”, the operation in “op”, and the operation's parameters as extra form fields.
Fast operations may complete on the first poll; heavy ones (OCR, conversions) take longer — poll every couple of seconds.
Every operation in the catalog is available identically over REST and MCP, with the same key and the same counters.

The machine-readable operation catalog (names, parameters, JSON Schemas) is served at GET https://api.pdfmcp.org/v1/operations — generate your client from it instead of hard-coding anything.

Troubleshooting

401 / unauthorized: the key header is missing or mistyped. The header name is exactly X-API-Key (Claude Code uses Authorization: Bearer … — both work).
Tools don't appear: fully restart the client after editing its config; most clients only load MCP servers at startup.
Server unreachable: check the public status page — and your network's outbound HTTPS to mcp.pdfmcp.org.

Try it with

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.API · MCPPDF to Word (DOCX)Convert a PDF to an editable Word document. Text-based conversion: paragraphs and headings are reconstructed from the text layer; exact layout, tables and images are not preserved.

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