Papyrio PDF Tools

io.github.atabekdemurtazaPublished by GitHub account atabekdemurtazav0.1.4Updated Oct 29, 2026

Compress, convert, merge, split and OCR PDFs from an assistant, using local files.

VerifiedSTDIODesktop onlyProductivity & Workflow Files & Storage

Server details

Identifier: io.github.atabekdemurtaza/papyrio-mcp
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Oct 13, 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 atabekdemurtaza 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.atabekdemurtaza%2Fpapyrio-mcp.svg)](https://sourceweft.com/mcp/io.github.atabekdemurtaza%2Fpapyrio-mcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Local MCP server that lets an assistant compress, merge, split, OCR and convert PDFs and Office files on your machine via the Papyrio API.

What you can do: Compress, merge, split and encrypt or unlock PDFs, writing results to local paths
Extract text from PDFs and add a searchable text layer to scans with OCR
Convert PDFs to Word or JPG, and Office documents or images to PDF
Render a public web page to PDF in a headless browser
Chain several steps in one request, e.g. OCR a folder of scans, merge and compress them
When to use it: Useful when you want an assistant to handle everyday PDF chores on local files — shrinking a file for email, joining scans or invoices, OCR-ing a scan before reading it, or turning a document into another format — without manual upload and download between steps.
Requirements: Runs locally over stdio via npx (Node.js) or a one-click Claude Desktop bundle. Optional PAPYRIO_API_KEY (RapidAPI subscription key) as an environment variable; without it the free guest tier allows three operations a day per IP address. Network access to the Papyrio API is required. Tools take absolute file paths.

Before you install

Files are uploaded to the Papyrio API for processing, so anything confidential leaves your machine. Most tools write to output_path and overwrite an existing file there. protect_pdf and unlock_pdf handle document passwords, which are passed to the service. The guest tier is capped at three operations a day; a paid RapidAPI subscription may be needed for regular use.

Installation

In SourceWeft

Open Papyrio PDF Tools in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

papyrio-mcp

[npm] [Listed on mcpservers.org] [Glama score]

An MCP server for the Papyrio PDF API. Setup for Claude, Cursor and VS Code: papyrio.net/mcp. It lets an assistant compress, merge, OCR and convert PDFs on your own machine, reading and writing local files, so multi-step work does not mean uploading and downloading between every step.

is four tool calls the assistant makes by itself.

Install

Claude Desktop, one click

[Watch: add PDF tools to Claude Desktop in one click (47 s)]

Download papyrio-mcp.mcpb and double-click it. Claude Desktop opens an install screen; leave the API key empty for the free guest tier or paste a RapidAPI key (see below). You can change it later under Settings, Extensions.

By hand, or any other client

Add this to your Claude Desktop config:

macOS ~/Library/Application Support/Claude/claude_desktop_config.json Windows %APPDATA%\Claude\claude_desktop_config.json

json

{  "mcpServers": {    "papyrio": {      "command": "npx",      "args": ["-y", "papyrio-mcp"]    }  }}

{  "mcpServers": {    "papyrio": {      "command": "npx",      "args": ["-y", "papyrio-mcp"]    }  }}

Restart Claude Desktop. The tools appear under the connector icon.

API key

The server works without one, metered as ordinary free web traffic: three operations a day per IP address. Enough to see whether it is useful.

For real use, subscribe on RapidAPI and pass the key:

json

{  "mcpServers": {    "papyrio": {      "command": "npx",      "args": ["-y", "papyrio-mcp"],      "env": { "PAPYRIO_API_KEY": "your-rapidapi-key" }    }  }}

{  "mcpServers": {    "papyrio": {      "command": "npx",      "args": ["-y", "papyrio-mcp"],      "env": { "PAPYRIO_API_KEY": "your-rapidapi-key" }    }  }}

The free RapidAPI tier is 50 requests a month and needs no card.

Tools

Tool	Does	Writes
`compress_pdf`	Shrinks a PDF, 30–80% on image-heavy files	`.pdf`
`merge_pdfs`	Joins 2–10 PDFs in order	`.pdf`
`split_pdf`	Separates every page into its own file	`.zip`
`extract_pdf_text`	Returns the text layer as UTF-8	`.txt`
`pdf_to_word`	Rebuilds the document as an editable .docx	`.docx`
`pdf_to_jpg`	Renders every page as a JPG	`.zip`
`ocr_pdf`	Adds a searchable text layer to a scan, up to 15 pages per call; `lang` picks English, Russian, Spanish, Italian, Uzbek or Kazakh	`.pdf`
`office_to_pdf`	Word, PowerPoint or Excel to PDF	`.pdf`
`image_to_pdf`	Wraps a JPG, PNG or WebP in a PDF page	`.pdf`
`webpage_to_pdf`	Renders a public URL in a headless browser	`.pdf`
`protect_pdf`	Encrypts with AES-256	`.pdf`
`unlock_pdf`	Removes a password you already know	`.pdf`

Every tool takes absolute paths. output_path is optional and defaults to the input name with a -papyrio suffix — except webpage_to_pdf, which has no input file to derive a name from and so requires it.

Adding a tool

Add an entry to src/tools.ts. The MCP tool, its input schema and the HTTP call are all generated from it.

Testing

Drives all twelve tools over the real MCP protocol against the live API and checks the returned file's magic bytes, so a JSON error body named .pdf fails rather than passes. Without a key it runs on the guest tier, where three operations a day means most cases will hit rate_limit_exceeded.

Develop

Point your config at the local build while working on it:

json

{  "mcpServers": {    "papyrio": {      "command": "node",      "args": ["/absolute/path/to/mcp/dist/index.js"]    }  }}

{  "mcpServers": {    "papyrio": {      "command": "node",      "args": ["/absolute/path/to/mcp/dist/index.js"]    }  }}

Privacy: files are sent to the Papyrio API, processed in memory, and discarded when the response is sent. Nothing is stored.

Licence

MIT

Source: README.md at commit 7ed2471

Tools

compress_pdf

Shrink a PDF by downsampling its images. Image-heavy files lose 30-80% of their size; text stays selectable. Use this when a PDF is too large to email or upload. Already-optimized files come back unchanged rather than larger. The input is uploaded to the Papyrio API, processed in memory and not stored. The result is written to output_path, replacing any file already there, and the call returns that path and the size in bytes. Inputs are limited to 50 MB, and each call counts as one operation against the daily quota.

Parametersfilerequiredleveloutput_path

merge_pdfs

Combine 2 to 10 PDFs into one document, in the order given. Use this to join separate scans, chapters or invoices into a single file. Password-protected files must be unlocked first. The input is uploaded to the Papyrio API, processed in memory and not stored. The result is written to output_path, replacing any file already there, and the call returns that path and the size in bytes. Inputs are limited to 50 MB, and each call counts as one operation against the daily quota.

Parametersfilesrequiredoutput_path

extract_pdf_text

Return the text of a PDF as UTF-8, so it can be read or summarized. Fast and exact when the PDF already has a text layer. A scanned PDF has none — run ocr_pdf on it first. The input is uploaded to the Papyrio API, processed in memory and not stored. The result is written to output_path, replacing any file already there, and the call returns that path and the size in bytes. Inputs are limited to 50 MB, and each call counts as one operation against the daily quota.