Integration

PDF Blocks integration

PDF Blocks is a stateless PDF processing API: send a PDF file, get the processed PDF back as a file. Merge up to ten PDFs, split one by page count, at a page, by file size or into custom page groups (the parts come back as one ZIP file), extract, remove, rotate, reverse or reorder pages, stamp a text or image watermark, add or remove an open password, add or remove permission restrictions (printing, copying, editing), and strip digital signatures. Nothing is stored after a call. Input files are capped at 5 MB on the Free plan and 10 MB on paid plans. Calls go to the global endpoint; the regional data-residency hosts are not exposed. Authentication is an API key from the PDF Blocks dashboard, sent in the X-API-Key header.

Connect PDF Blocks How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PDF Blocks.Built from the 17 PDF Blocks tools below, on the connection you add once.

What you can do with PDF Blocks

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.

Add password, 1 operation

add_passwordAdd passwordPOSTEncrypts a PDF with an open password, so it cannot be opened without it. Returns the encrypted PDF as a file; pages and content are unchanged. Choose AES-128 (default) or AES-256.

Add restriction, 1 operation

add_restrictionsAdd restrictionsPOSTProtects a PDF with an owner password and turns off chosen permissions (copying, editing, printing, form filling, page assembly, accessibility). Every flag defaults to true; set the ones to block to false. Returns the restricted PDF.

Add watermark, 1 operation

add_text_watermarkAdd text watermarkPOSTStamps up to three lines of text (32 characters each) on every page of a PDF, or on chosen pages, with a template (filled or outline, diagonal, horizontal or vertical), color and transparency. Returns the watermarked PDF.

Extract page, 1 operation

extract_pagesExtract pagesPOSTKeeps only the chosen pages of a PDF, in document order, and returns them as a new PDF. A page number past the end of the document is refused.

Image, 1 operation

add_image_watermarkAdd image watermarkPOSTStamps a PNG or JPEG image, such as a logo, on every page of a PDF or on chosen pages, with a transparency and margin. Returns the watermarked PDF.

Merge document, 1 operation

merge_documentsMerge documentsPOSTCombines up to ten PDF files into one, in numeric order (file_1 first). The merged PDF has the pages of every input, in that order.

Remove page, 1 operation

remove_pagesRemove pagesPOSTDeletes the chosen pages from a PDF and returns the rest in their original order. At least one page must remain.

Remove password, 1 operation

remove_passwordRemove passwordPOSTDecrypts a password-protected PDF using its current password, so it opens without one. Returns the decrypted PDF; a wrong password is refused.

Remove restriction, 1 operation

remove_restrictionsRemove restrictionsPOSTClears the permission flags (printing, copying, editing) from a PDF and returns the unrestricted document; pages and content are unchanged.

Remove signature, 1 operation

remove_signaturesRemove signaturesPOSTStrips every digital signature and timestamp from a PDF so it can be edited, and returns the document; pages and content are unchanged.

Reorder page, 1 operation

reorder_pagesReorder pagesPOSTRearranges the pages of a PDF into the order given in page_order. Pages left out are dropped and a page listed twice is repeated, so it also extracts and duplicates pages. Returns the new PDF.

Reverse page, 1 operation

reverse_pagesReverse pagesPOSTReverses the page order of a PDF (last page first) and returns the new PDF; each page keeps its content and size.

Rotate page, 1 operation

rotate_pagesRotate pagesPOSTRotates every page of a PDF, or the chosen pages, by 90, 180 or 270 degrees (negative angles turn counter-clockwise). Returns the rotated PDF.

Split at page, 1 operation

split_at_pageSplit at pagePOSTSplits a PDF in two at a page: the pages before it form the first part, that page and the rest the second. Returns both parts in one ZIP file.

Split by group, 1 operation

split_by_groupsSplit by groupsPOSTSplits a PDF into page groups you define, one output PDF per group in the order written. Returns the parts in one ZIP file.

Split by page count, 1 operation

split_by_page_countSplit by page countPOSTSplits a PDF into consecutive parts of a fixed number of pages; the last part holds the remaining pages. Returns the parts in one ZIP file.

Split by size, 1 operation

split_by_sizeSplit by sizePOSTSplits a PDF into parts each no larger than a byte limit; a single page bigger than the limit becomes its own oversized part. Returns the parts in one ZIP file.

Use PDF Blocks from Claude Code, Cursor or Codex

Connect PDF Blocks in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its PDF Blocks 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 PDF Blocks

Create your workspace
Sign up free. Nothing to install.
Connect PDF Blocks once
Add your PDF Blocks 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.