Merge, split, stamp and read PDFs, pure JavaScript, no upload. It merges and splits PDFs, extracts and reorders pages, rotates a sideways scan, stamps PAID or DRAFT or any text, watermarks the business name and VAT id from the shared profile, and reads text back best effort with no OCR.
The pattern that saves the most time here is asking in the same chat that just generated a docx proposal: print it, then merge it with a signed cover page before it goes out.
| You say | Tool |
|---|---|
| Stamp PAID on this invoice and save a copy. | pdf_stamp |
| Join these three PDFs into one file. | pdf_merge |
| Split the scan: pages 1-3 are the invoice, 4 onwards is the receipt. | pdf_split |
The worked run stamped PAID on a 1-page invoice and wrote a new 0.9 MB file; the original file was byte-for-byte unchanged, which every writing tool here guarantees on purpose.
The file is .cursor/mcp.json, and the key inside it is mcpServers.
| Scope | Path |
|---|---|
| This project only | <project>/.cursor/mcp.json |
| Every project | ~/.cursor/mcp.json |
If you also run Claude Desktop, the shortest path there is one click: pdf.mcpb
from the bundle catalog opens as an extension, with no JSON and no terminal.
Cursor reads its own config, so here it is:
The config block:
{
"mcpServers": {
"pdf": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/mcp-servers/servers/pdf/dist/index.js"]
}
}
}The node command above wants a built file. From a clone, once:
git clone https://github.com/theluckystrike/mcp-servers.git
cd mcp-servers && npm install
npm run build -w packages/mcp-license -w servers/pdfThat writes servers/pdf/dist/index.js, and its absolute path is the one argument
the config needs.
The npm packages are not published yet, so the form below returns a 404 today. It is here because it is what the entry becomes the day the publish lands, with nothing else changed:
{
"mcpServers": {
"pdf": {
"command": "npx",
"args": ["-y", "@theluckystrike/mcp-pdf"]
}
}
}The Customize page shows the server and its tools once it has started.
Nothing is published to npm yet, so the working install paths are the ones above: the .mcpb bundle from the bundle catalog, a clone and build, or the hosted URL.
The same server runs at https://mcp.zovo.one/mcp/pdf over MCP streamable HTTP, no install. Mint a free token with curl https://mcp.zovo.one/mcp/token, or use a Pro key. It has no filesystem, so a file comes back as a one-hour download link.
{
"mcpServers": {
"pdf": {
"url": "https://mcp.zovo.one/mcp/pdf",
"headers": { "Authorization": "Bearer <token>" }
}
}
}The current field table marks `type` as required, with `stdio` for a locally launched server, so write it out rather than relying on command and args alone. The other documented restriction is that `envFile` is stdio-only: a remote HTTP or SSE server does not read it, and its headers belong in the config.
Free: info, count and text unlimited; merge up to 5 files; edits on files up to 30 pages; the PAID and DRAFT stamp presets. Pro is $19 once, verified offline.
<project>/.cursor/mcp.json applies to that project and can be committed, which suits a server tied to one client. ~/.cursor/mcp.json applies everywhere. Both are managed from the Customize page.
The current field table marks type as required, with stdio for a locally launched server, so include it. Pointing at a remote endpoint, envFile is documented as stdio-only and is not read.
Servers in Cursor's marketplace get an Add to Cursor button. The deeplink reference currently documents prompt, command and rule links only, so for MCP PDF Tools pasting the config block above is the supported route.
MCP PDF Tools in detail · The same server in Claude Code and VS Code · Every server in Cursor · Guides · Cursor docs · Buy Pro
Merge, split and stamp PDFs from chat, and why some come back as glyph numbers · Price drop alerts and PDF cleanup from chat: two small jobs you keep postponing · Splitting one big scan into separate documents · Merging a folder of receipts into one PDF from chat