Integration

PDF4me integration

PDF4me document processing API: convert office documents, HTML and web pages to PDF, turn a PDF back into Word, run OCR on a scan to make it searchable, merge documents, stamp text onto pages, compress a file, fill a fillable form and generate barcode images. Every call takes its input as base64 text inside the JSON body and answers with the produced file itself rather than with a link to it. Requests authenticate with an API key sent in the Authorization header behind the word Basic.

Connect PDF4me How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PDF4me.Built from the 10 PDF4me tools below, on the connection you add once.

Common PDF4me use cases

archiving a published page
binding a cover to a report
marking a draft as confidential
putting a tracking code on a label
shrinking a scan before sending it
filling an application form from record data
reworking a PDF contract in a word processor
preparing a scanned archive for full text search
producing a printable report from generated markup
turning a Word contract into a PDF before signature

What you can do with PDF4me

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Pdf, 7 operations

add_text_stampAdd text stampPOSTStamps text such as a watermark or a reference onto the pages of a PDF.
compress_pdfCompress pdfPOSTCompresses a PDF with a named optimisation profile.
convert_html_to_pdfConvert html to pdfPOSTRenders HTML markup into a PDF with full control over the page setup.
convert_to_pdfConvert to pdfPOSTConverts an office document or an image into a PDF.
convert_url_to_pdfConvert url to pdfPOSTRenders a web page into a PDF, optionally passing credentials to reach it.
merge_pdfsMerge pdfsPOSTMerges several PDFs, each supplied as base64 text, into one document.
ocr_pdfOcr pdfPOSTMakes a scanned PDF searchable by running text recognition over its pages.

Barcode, 1 operation

create_barcodeCreate barcodePOSTGenerates a barcode or QR code as an image.

Document, 1 operation

convert_pdf_to_wordConvert pdf to wordPOSTConverts a PDF back into an editable Word document.

Form, 1 operation

fill_pdf_formFill pdf formPOSTFills a fillable PDF form and returns the completed document.

Use PDF4me from Claude Code, Cursor or Codex

Connect PDF4me in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its PDF4me operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect PDF4me

Create your workspace
Sign up free. Nothing to install.
Connect PDF4me once
Add your PDF4me connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

PDF4me integration FAQ

What can you do with the PDF4me integration?

LiveContext exposes 10 operations on PDF4me, covering pdf, barcode, document and form. Common uses include archiving a published page, binding a cover to a report and marking a draft as confidential.