Split Pdf

io.github.theluckystrikePublished by GitHub account theluckystrikev0.21.1Updated Oct 24, 2026

Merge, split, extract, rotate, reorder and stamp PDF pages from your AI chat, all offline.

The publisher's own server: Split (creator affiliate platform)

VerifiedStreamable HTTPWeb executableProductivity & Workflow Files & Storage

Server details

Identifier: io.github.theluckystrike/split-pdf
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account theluckystrike for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.theluckystrike%2Fsplit-pdf.svg)](https://sourceweft.com/mcp/io.github.theluckystrike%2Fsplit-pdf?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

MCP server that lets an assistant merge, split, extract, rotate, reorder, stamp and read PDF pages, either locally or via a hosted endpoint.

What you can do: Inspect and count PDFs: page sizes, paper name, metadata, encryption flag, page totals across many files
Merge, split by page range, extract or reorder pages into new PDFs
Rotate pages and stamp text such as PAID or DRAFT, or add a business name and VAT id footer
Extract text from standard-font PDFs on a best-effort basis
Manage hosted storage: upload a PDF, list stored files, delete one
Check licence state and activate a Pro key
When to use it: Useful when you want routine page-level PDF chores done from chat instead of a web uploader: joining scans, pulling out a page range, turning a sideways scan, marking an invoice PAID, or reading text back from a generated PDF.
Requirements: Either the remote endpoint at mcp.zovo.one with a bearer token in the Authorization header, or a local install via the .mcpb bundle or a clone-and-build (Node.js 18 or newer; the npm package is described as not yet published). A Pro licence key (MCP_LICENSE_KEY or license_activate) is optional for paid features. The hosted endpoint has no filesystem, so files must be uploaded first.

Before you install

The remote endpoint requires a bearer token and stores uploaded PDFs under that token, so documents leave your machine; the local build is described as making no network requests. Writes create new files and refuse to overwrite unless overwrite is true, and encrypted PDFs are refused. Pro features cost a one-time fee. Text extraction has no OCR and can return glyph indices for custom fonts.

Installation

In SourceWeft

Open Split Pdf in the dashboard and add it to a workspace.
Connect Authorization token credentials. They are stored privately and never shown on public pages.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.theluckystrike%2Fsplit-pdf/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "split-pdf": {
      "type": "http",
      "url": "https://mcp.zovo.one/mcp/split-pdf",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Merge, split and fill PDF forms from Claude

Say "stamp PAID on that invoice and save a copy" or "pull pages 2 to 6 out of this scan and merge them with the contract" and it happens, on your machine, in a second. This MCP server does the small PDF jobs that otherwise send you to a web uploader: merge, split by page range, extract or reorder pages, rotate a sideways scan, stamp PAID or DRAFT or any text you like, put your business name and VAT id in the footer, count pages across a folder of files, and read a PDF's text back as text. No upload, no account, no native dependency, no office install.

In the official MCP Registry (io.github.theluckystrike/pdf-merge-split-stamp-extract-pages).

Listed on the AI Product Index - live remote endpoint at mcp.zovo.one/s/pdf, free tier, no signup.

[pdf demo]

The PDF chores of a freelance business, done from chat instead of from a browser tab you do not trust with an invoice.

60-second install

npm publish for @theluckystrike/mcp-pdf is pending. Until then, the .mcpb one-click bundle or a clone+build is the working path, both are verified below.

One-click (.mcpb): download pdf.mcpb from the latest release and double-click it in Claude Desktop: https://github.com/theluckystrike/mcp-servers/releases/latest

(claude_desktop_config.json):

json

{  "mcpServers": {    "pdf": {      "command": "npx",      "args": ["-y", "@theluckystrike/mcp-pdf"]    }  }}

{  "mcpServers": {    "pdf": {      "command": "npx",      "args": ["-y", "@theluckystrike/mcp-pdf"]    }  }}

Claude Code:

(.cursor/mcp.json):

json

{  "mcpServers": {    "pdf": {      "command": "npx",      "args": ["-y", "@theluckystrike/mcp-pdf"]    }  }}

{  "mcpServers": {    "pdf": {      "command": "npx",      "args": ["-y", "@theluckystrike/mcp-pdf"]    }  }}

The npx form above starts working the moment the package is published. Until then, use the .mcpb bundle above, or build from source with exactly these three commands:

git clone https://github.com/theluckystrike/mcp-servers.git && cd mcp-serversnpm installnpm run build -w packages/mcp-license -w servers/pdf

git clone https://github.com/theluckystrike/mcp-servers.git && cd mcp-serversnpm installnpm run build -w packages/mcp-license -w servers/pdf

Then point your client's command at node with one arg: the absolute path to servers/pdf/dist/index.js.

To run in Pro mode set MCP_LICENSE_KEY in the same config block, or call license_activate once with your key.

Tools

Tool	What it does
`pdf_info`	Page count, every page's size in points and millimetres, the paper name (A4, Letter, custom), the rotation already on each page, the metadata (title, author, producer, dates) and whether the file is encrypted
`pdf_count`	Page count per file plus the total, for any number of PDFs. A file it cannot read is reported per file; the rest still count
`pdf_merge`	Join PDFs into one, in the order given. Page sizes are kept as they are, and a merged file with mixed sizes says so
`pdf_split`	One new file per range. `"1-3,5,7-"` gives pages 1-3, page 5, and page 7 to the end. `out_path_pattern` takes `{n}`, `{range}` and `{name}`
`pdf_pages`	Extract selected pages into one new PDF, in the order you write them. `"5,1,1"` puts page 5 first and page 1 in twice
`pdf_rotate`	Turn pages by a multiple of 90 degrees, added to the rotation the page already had, which is what a sideways scan needs
`pdf_stamp`	Draw text on the pages: `PAID` and `DRAFT` presets, or any text, colour, position, opacity and size. Centre stamps go on the 45-degree diagonal
`pdf_watermark_business`	Your business name and VAT id in the footer of every page, from the shared profile mcp-invoice and mcp-docx write
`pdf_text`	Best-effort text extraction from the page content streams. See the honest caveats below
`pdf_reorder`	Write a new PDF with the pages in a new order. The order must name every page exactly once, so nothing is dropped by accident
`license_status`	Show free or Pro mode
`license_activate`	Activate a Pro key (verified offline)

Resource: pdf://recent returns the last 25 operations, newest first, with the inputs, the files written and when. Prompt: mark_invoice_paid chains mcp-invoice's invoice_get into pdf_stamp PAID and saves the stamped copy beside the original.

What you can say

You say	Tool
"Mark invoice INV-2026-0007 as paid."	`mark_invoice_paid` prompt, then `pdf_stamp`
"Stamp DRAFT across this contract before I send it."	`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`
"Pull pages 2 to 6 out of this and save them separately."	`pdf_pages`
"This scan is sideways, turn it."	`pdf_rotate`
"How many pages are in all of these?"	`pdf_count`
"What does page 1 of this PDF say?"	`pdf_text`
"Put my company name and VAT number in the footer."	`pdf_watermark_business`
"Move the cover page to the front."	`pdf_reorder`

Worked example

You: Stamp PAID on ~/invoices/INV-2026-0007.pdf and save a copy.
  pdf_stamp {    path: "~/invoices/INV-2026-0007.pdf",    text: "PAID",    position: "center",    out_path: "~/invoices/INV-2026-0007-paid.pdf"  }  -> Stamped "PAID" on 1 page  -> ~/invoices/INV-2026-0007-paid.pdf, 0.9 MB

You: Stamp PAID on ~/invoices/INV-2026-0007.pdf and save a copy.
  pdf_stamp {    path: "~/invoices/INV-2026-0007.pdf",    text: "PAID",    position: "center",    out_path: "~/invoices/INV-2026-0007-paid.pdf"  }  -> Stamped "PAID" on 1 page  -> ~/invoices/INV-2026-0007-paid.pdf, 0.9 MB

The stamp is drawn text, not a flattened image: it can be selected and searched, it is drawn on the 45-degree diagonal in the preset green, and the original file is byte-for-byte unchanged.

Free vs Pro

	Free	Pro
`pdf_info`, `pdf_count`, `pdf_text`	Unlimited	Unlimited
`pdf_merge`	Up to 5 files per call	Any number of files
`pdf_split`, `pdf_pages`, `pdf_rotate`	Files up to 30 pages	Any length
`pdf_stamp`	The `PAID` and `DRAFT` presets in their preset colours	Any text, any colour, any size
`pdf_watermark_business`	-	Your business name and VAT id in the footer
`pdf_reorder`	-	Yes

A tier limit is an answer, not an error, and nothing is written when one refuses a call.

Pro is a one-time $19, or $39 for every server in the collection, lifetime.

`pdf_text` is best effort, and here is exactly what that means

A PDF does not store text. It stores drawing operators, and the text you see is bytes handed to a font. This server decompresses each page's FlateDecode content stream with node:zlib and reads the four text-showing operators -- Tj, TJ, ' and ", plus the positioning operators that end a line. That is a parser written here, in about two hundred lines, with no pdfjs and no native module, and it has three real limits the tool states in its own answer every time:

A scan has no text. An image-only page carries no text operators, so nothing comes back. There is no OCR here and there will not be one; the answer says the page is probably a scan rather than returning an empty string with no explanation.
A custom or CID encoding returns glyph indices, not letters. Subset-embedded and CJK fonts map bytes to glyph numbers through a table this parser does not read. When the output has no readable characters, the answer says the font is the reason.
Reading order is drawing order. There is no column detection and no layout reconstruction. Word spaces are recovered from the large negative kerns a TJ array uses for them, so a PDF that positions every word separately can come back with words run together.

PDFs written by word processors, invoicing tools and report generators, everything with a standard or fully embedded font, read back cleanly. Anything else tells you why it did not.

Encrypted PDFs are refused, not guessed

pdf-lib cannot decrypt, and loading an encrypted file while ignoring the encryption produces pages of garbage that would be written straight into the output. So a file whose trailer names an /Encrypt dictionary is refused by every tool that writes, with the reason and the fix in the message: open it in a reader with the password, export or print to a new PDF, and use that file. pdf_info still answers, with encrypted: true, because reporting is its whole job, and pdf_count reports it as one unreadable file while still counting the rest.

Existing files are never overwritten, and inputs are never modified

Every tool writes a new file and leaves its inputs byte-for-byte alone, there is no in-place mode, on purpose. An out_path that already exists is refused:

Error: /path/merged.pdf already exists and nothing was written.Pass overwrite: true to replace it, or give a different out_path.

Error: /path/merged.pdf already exists and nothing was written.Pass overwrite: true to replace it, or give a different out_path.

The path is reserved with an exclusive create, not an existence check, so two processes writing the same out_path at the same time cannot clobber each other: one wins, the other is refused and writes nothing. pdf_split reserves every one of its output paths before it writes any of them, so a collision on part 3 does not leave parts 1 and 2 behind as a half-done split, and the reservations are released, so nothing empty is left on disk either.

Pass overwrite: true when replacing the file is what you want.

overwrite: true still does not let an output be an input. Writing the result of an operation back over one of its own sources destroys that source, the pages are already in memory and get written over the file they came from, which takes a three-page file to the one page you extracted, and every later read of that path is then quietly wrong. So an out_path that resolves to (or shares an inode with) any input of the same call is refused before any work happens:

Error: out_path /path/scan.pdf is also an input of this operation, so writing it would destroy the source.Nothing was written. Write beside it instead - /path/scan-out.pdf - and, if the result really is meant totake the original's place, rename it yourself once you have checked it.

Error: out_path /path/scan.pdf is also an input of this operation, so writing it would destroy the source.Nothing was written. Write beside it instead - /path/scan-out.pdf - and, if the result really is meant totake the original's place, rename it yourself once you have checked it.

Limits

Inputs over 100 MB are refused: rewriting a PDF needs several times its size in memory.
A file that does not start with %PDF- is refused before anything is read.
Rotation is recorded as page metadata, in multiples of 90 degrees, which is all the format has. Nothing is redrawn.
Stamp text goes through a built-in PDF font, which carries WinAnsi and its 256 code points. A character outside it is transliterated where it has an obvious Latin body, Polish OPŁACONE stamps as OPLACONE, and the answer says so and prints what was actually drawn, and removed and counted where it does not, so there is no CJK stamp. A newline is a word separator, never a deletion.
font_size must be between 1 and 1600 points. A stamp too long to fit even at the smallest size this server will use is still drawn, and the answer says how far past the edge it runs, so you can shorten it.
pdf_text caps one answer at 200,000 characters and names the pages argument that continues from where it stopped. Nothing is missing from the file; the cut is in the answer, not the read.
No page numbering, no signatures, no redaction, no compression. This server does the page-level jobs; it is not a PDF editor. It does not write PDF/A: pdf_info reports a file's own pdfa_claim, and every tool that writes says plainly that its output no longer holds that claim.
Forms are read, not filled: pdf_text prints the AcroForm field values, which live in the fields rather than in the page content stream and are therefore not part of the page text.
No OCR. See the pdf_text section.

How it stores data

Only a register of what it did: ${XDG_DATA_HOME:-~/.local/share}/mcp-servers/pdf/operations.json, the last 500 operations, as plain JSON. Your PDFs stay where you put them. Every write to the register runs inside an advisory lock on .../pdf/.lock, so two clients on one data directory cannot lose a record, and saves go to a temporary file and are renamed into place.

If the register is unreadable or not valid JSON it is never treated as "empty": it is moved aside byte-for-byte as operations.json.corrupt-<timestamp> with a marker beside it. The PDF you asked for is still written, the file is on disk before the register is touched, and the answer tells you the history could not be updated.

The business footer reads the one shared profile the whole suite uses, ${XDG_DATA_HOME:-~/.local/share}/mcp-servers/profile/business.json, written by business_set in mcp-invoice or mcp-docx. Nothing is invented: with no name stored, pdf_watermark_business refuses and says which tool to run.

Privacy

All data stays local. The server reads and writes files on your machine and makes no network request of any kind -- not for licensing (keys are verified offline), not for fonts, not for telemetry. A PDF you stamp is never uploaded anywhere, which is the entire reason this exists.

Pairs with

mcp-invoice, the invoice you sent, stamped PAID: the mark_invoice_paid prompt chains invoice_get into pdf_stamp.
mcp-docx, write the proposal as .docx, print it to PDF, then stamp, merge or split it here.
mcp-resume, join a CV, a cover letter and a portfolio into the one file an application form accepts.
office-suite, several servers behind one install, one config entry.

Troubleshooting

npx hangs or fails to find the package: npm publish for this package is pending. Use the .mcpb bundle or the clone-and-build path above until it lands.
"is encrypted and was refused": the file is password or permissions protected. Open it in a PDF reader, export or print to a new PDF, and run the tool on that copy. This server never guesses or strips a password.
pdf_text returned nothing: the page is a scan, or its font uses a custom encoding. The answer says which. There is no OCR here.
The stamp is too small or too big: by default it is sized to fit the page width. Pass font_size for an exact point size, and opacity between 0 and 1.
"already exists and nothing was written": pass overwrite: true, or a different out_path.
Node version: requires Node >= 18. Check with node -v.

MIT licensed. Support: [email protected]

Built by theluckystrike.

Frequently asked questions

Is there an MCP server to merge and split PDFs?

Yes. The pdf server at mcp.zovo.one merges, splits, rotates and fills PDF forms while preserving form fields. Free tier of 30 pages per file on split/pages/rotate operations, hosted remote endpoint, no install.

Can Claude fill PDF forms with an MCP server?

Yes - connect https://mcp.zovo.one/mcp/pdf and ask Claude to fill a form's fields or merge several PDFs. Output stays form-preserving, so filled fields remain editable.

Use these docs as an MCP server

Any MCP client (Claude, Cursor, Windsurf, VS Code) can read this repository's documentation directly via GitMCP - no install:

Docs MCP URL: https://gitmcp.io/theluckystrike/mcp-pdf

Source: servers/pdf/README.md at commit 6535b33

Tools

pdf_info

Inspect a PDF

Call this tool to inspect a PDF: page count, page sizes in points/mm, paper name, metadata (title, author, producer, dates) and whether it is encrypted. Read-only, never modifies the file. Free tier: unlimited.

Parameterspathrequired

pdf_count

Count pages in several PDFs

Page count per file plus the total, for any number of PDFs, with how many were readable. A file that cannot be read is reported on its own row and the others still count. Read-only. Free and unlimited.

Parameterspathsrequired

pdf_merge

Merge PDFs into one file

Call this tool to join several PDFs into one, in the order given. Page sizes are kept as-is, so a merged file may have mixed sizes, and the answer says so. Inputs are never modified. Free tier: up to 5 files per merge.

Parameterspathsrequiredout_pathrequiredoverwrite

pdf_split

Split a PDF into several files

Call this tool to write one new PDF per range. Ranges are 1-based and may be open-ended: "1-3,5,7-" gives pages 1-3, page 5, and 7 to the end. The input is never modified. Free tier: files up to 30 pages.

Parameterspathrequiredrangesrequiredoverwriteout_path_patternrequired

pdf_pages

Extract pages into a new PDF

Call this tool to pull selected pages into one new PDF, in the order written: "2,4-6" gives four pages. Asking for a page twice copies it twice. The input is never modified. Free tier: files up to 30 pages.

Parameterspathrequiredpagesrequiredout_pathrequiredoverwrite

pdf_rotate

Rotate pages

Call this tool to turn pages by a multiple of 90 degrees, clockwise for positive. Rotation is added to whatever the page already had, for a sideways scan. Writes a new file. Free tier: files up to 30 pages.

Parameterspathrequiredpagesdegreesrequiredout_pathrequiredoverwrite

pdf_stamp

Stamp text on a PDF

Call this tool to draw a word such as PAID or DRAFT across the pages, in a colour and position you choose. Writes a new file; input untouched. Free tier: the PAID and DRAFT presets in their preset colours.

Parameterspathrequiredtextrequiredcolorpagesopacityout_pathrequiredpositionfont_sizeoverwrite

pdf_watermark_business

Stamp your business details in the footer

Call this tool to put your business name and VAT id in the footer of every page, from the shared profile mcp-invoice and mcp-docx write. Use it before sending a document out. Pro.

Parameterspathrequiredpagesout_pathrequiredoverwrite

pdf_reorder

Reorder the pages of a PDF

Call this tool to write a new PDF with pages in the order you give. The order must name every page exactly once, so nothing drops by accident; use pdf_pages for a subset. Pro.

Parameterspathrequiredorderrequiredout_pathrequiredoverwrite

pdf_text

Read the text of a PDF

Call this tool for best-effort text extraction from standard-font PDFs. Returns nothing for a scan (no OCR), or glyph indices for a custom-encoded font, and says which case applies. Read-only. Free tier: unlimited.

Parameterspathrequiredpages

license_status

License status

Report this endpoint's licence state for your token as JSON: the product, the tier free or pro, why it is not Pro, and the checkout URL. Call it to explain a free-tier refusal. No arguments, nothing changes.

Takes no parameters.

license_activate

Activate license

Turn Pro on for this connection with key, an MCPL1.<payload>.<signature> issued at checkout for this server or the bundle. Data under your token stays; a wrong or expired key changes nothing. license_status confirms it.

Parameterskeyrequired

pdf_upload

Upload a PDF to work on

Send a PDF to this hosted endpoint. There is no filesystem here, so instead of a path you upload the file once with pdf_upload and then pass its name as `path` (or inside `paths`) to pdf_info, pdf_count, pdf_merge, pdf_split, pdf_pages, pdf_rotate, pdf_stamp, pdf_reorder and pdf_text. Give exactly one of pdf_base64 or url. url: fetch a public file instead of pasting base64 (recommended above about 10 KB): pasting a large base64 payload is slow to write out and can stall the turn before the call is ever sent, while a url costs one line and the fetch happens here. Uploads are kept for your token between calls; pdf_files lists them and pdf_delete_upload removes one. A file this server writes is named the same way and comes back as a download link valid for one hour. The request body cap is 256 KB, which is about 190 KB of PDF once base64-encoded; a url is fetched with a 10 second timeout, at most 3 redirects, public http(s) hosts only, and is capped at 2 MB.

Parametersurlnamerequiredpdf_base64

pdf_files

List uploaded and generated PDFs

List the PDFs stored for your token: what you uploaded, and what this server has written, with their sizes.

Takes no parameters.

pdf_delete_upload

Delete a stored PDF

Delete one PDF stored for your token, uploaded or generated.

Parametersnamerequired

Version history

v0.21.1LatestSep 23, 2026
v0.21.0Sep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts

Other Split integrations

Split (creator affiliate platform)

co.split.mcpOfficial publisher

Split's remote MCP endpoint lets an assistant work with a creator affiliate platform where creators earn on product links and brands run campaigns and gifting.

Streamable HTTPWeb executableAuth

Business & CommerceCredential requiredOct 24, 2026

Partly Exact Split

com.partly-app

A remote MCP server that splits shared expenses among 2–30 people and returns balances and reimbursement suggestions.

Streamable HTTPWeb executable

Productivity & Workflow1 toolOct 30, 2026

Eclipse Split

Published by GitHub account CYAN-ECLIPSE-TECHNOLOGIES-LLC

Local MCP server that seals pre-agreed revenue splits at spawn and settles them against completion records, in a local/fixture-only mode.

STDIODesktop only

FinanceNot validated yetOct 29, 2026

Trail Split

Published by GitHub account farssaadeldin7-ux

Trail Split is a local MCP plugin for expedition leaders that helps plan shared gear, food, weight and cost across a group trip.

STDIODesktop only

Location & LifestyleNot validated · the package type cannot run in the sandboxOct 26, 2026

RoomSplit

Published by GitHub account everyai-com

RoomSplit is a free remote MCP server that lets an assistant split rent and shared bills among housemates, settle balances, and draft a roommate agreement.

Streamable HTTPWeb executable

Productivity & Workflow4 toolsOct 25, 2026

Split Pdf

Overview

Installation

In SourceWeft

Use with an agent

Other MCP clients

README

Merge, split and fill PDF forms from Claude

60-second install

Tools

What you can say

Worked example

Free vs Pro

pdf_text is best effort, and here is exactly what that means

Encrypted PDFs are refused, not guessed

Existing files are never overwritten, and inputs are never modified

Limits

How it stores data

Privacy

Pairs with

Troubleshooting

Frequently asked questions

Is there an MCP server to merge and split PDFs?

Can Claude fill PDF forms with an MCP server?

Use these docs as an MCP server

Tools

pdf_info

pdf_count

pdf_merge

pdf_split

pdf_pages

pdf_rotate

pdf_stamp

pdf_watermark_business

pdf_reorder

pdf_text

license_status

license_activate

pdf_upload

pdf_files

pdf_delete_upload

Version history

Score

Other Split integrations

Split (creator affiliate platform)

Partly Exact Split

Eclipse Split

Trail Split

RoomSplit

`pdf_text` is best effort, and here is exactly what that means