mcpbeat Sign in

Papyrio PDF Tools MCP Server

by atabekdemurtaza Your server? Claim it
local only

Papyrio PDF Tools runs on your own machine — the client starts it, so there is no endpoint to ping. 598 installs a week from npm. Last commit 14 Oct 2026.

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

Installs per day peak 598 · avg 19
a month agotoday
598
Installs / week
npm · papyrio-mcp
1
Stars
0 open issues
14 Oct 2026
Last commit
from GitHub
MIT
License
TypeScript

Nothing serious here today

Today is the operative word: we check Papyrio PDF Tools every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add papyrio-mcp -- npx -y papyrio-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "papyrio-mcp": {
      "args": [
        "-y",
        "papyrio-mcp"
      ],
      "command": "npx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.papyrio-mcp]
command = "npx"
args = ["-y", "papyrio-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "papyrio-mcp": {
      "args": [
        "-y",
        "papyrio-mcp"
      ],
      "command": "npx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "papyrio-mcp": {
      "args": [
        "-y",
        "papyrio-mcp"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: PAPYRIO_API_KEY (RapidAPI subscription key. Without one the server runs on the free guest tier, which allows three operations a day per IP address.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Papyrio PDF Tools

same job, measured the same way
pdfAssistant
by pdfassistant

Convert, merge, compress, OCR, redact, and sign PDFs inside your AI assistant. From pdfAssistant.

answering
SmartPDF
by smartpdf

24 PDF tools: convert to and from Office and JPG, compress, merge, split, OCR, sign, watermark

48 tools answering
P
PDF
by yaktool

Merge, split, compress, unlock, organize, extract, fill forms and check PDFs — 12 local tools.

50 installs/wk local only
conv2pdf
by conv2pdf

Convert Office files, images and e-books to PDF; merge, compress or protect local PDFs.

55 installs/wk local only
Diemdesk
by diemdesk

Convert Office files and PDFs, OCR a scan, or capture a web page — from your assistant.

39 installs/wk local only
PDF Split Merge Compress
by theluckystrike

Split, merge and compress PDF files locally - private by design, no uploads.

15 tools answering
DicePDF
by ishan-maheshwari

Local-first PDF tools for AI agents: merge, split, extract, render, compress. Files stay on-device.

30 installs/wk local only
PDFHaul MCP
by pdfhaul-www

PDF tools: merge, split, compress, convert, OCR & more. OAuth with auto-registration or API key.

answering

Papyrio PDF Tools — questions

Answers built from our own checks of this server.

Why is there no uptime for Papyrio PDF Tools?
Papyrio PDF Tools runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package papyrio-mcp was installed 598 times last week.
How do I connect Papyrio PDF Tools?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls papyrio-mcp straight from npm; nothing to host, nothing to sign up for.
How many people use Papyrio PDF Tools?
The npm package papyrio-mcp was installed 598 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Papyrio PDF Tools open source?
Yes — it is published under the MIT licence, written in TypeScript and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.