ChamPDF for developers & AI agents

Every document, image, and video tool on this site also has a server-side API. Sign in, mint a key, and call it from your own code — or hand it straight to Claude, Cursor, or any other MCP-aware assistant.

1. Get an API key

Sign in (top right) — any account works, no separate application needed.
Click the API pill next to your avatar.
Click Generate API key and copy it — it's shown once.

Free tier: 1,000 requests / month, 30 requests / minute burst. Usage is visible any time via GET /api/v1/whoami.

2. Call it directly

Every endpoint lives under /api/v1 and takes an Authorization: Bearer champdf_live_... header. Example — strip the background from a photo:

curl -X POST https://champdf-api.64.227.154.215.sslip.io/api/v1/image/remove-bg \
  -H "Authorization: Bearer champdf_live_..." \
  -F "image=@photo.jpg" \
  -o photo-no-bg.png

Full endpoint list, request/response shapes, scopes, and error codes: /llms.txt (plain text, built for pasting into an AI tool) or the interactive Swagger docs.

3. Or hand it to your AI assistant

The @champ-deep/champdf-mcp package wraps this API as native tools for Claude Code, Claude Desktop, Cursor, and any other MCP-aware client — merge, split, sign, convert, OCR, remove backgrounds, and more, called directly from your conversation.

claude mcp add champdf \
  -e CHAMPDF_API_KEY=champdf_live_... \
  -e CHAMPDF_API_BASE_URL=https://champdf-api.64.227.154.215.sslip.io \
  -- npx -y @champ-deep/champdf-mcp

The API panel (step 1) fills this in with your real key and also shows the Claude Desktop / Cursor JSON config — just copy and paste.

What you can call

Area	Examples
Documents	merge, split, rotate, compress, watermark, info, to-text, to-images, from-images, sign, verify-signature, OCR, extract-tables
Convert	Office docs (Word/Excel/PowerPoint/ODF) → PDF, PDF → editable Word
Images	remove background, AI edit, detect watermarks, inpaint
Video	download, remove logo/watermark

Not every feature is enabled on every deployment — check GET /api/v1/capabilities to see what's currently on.

Good to know