PDF.co MCP Server

by pdfdotco Your server? Claim it

local only

PDF.co runs on your own machine — the client starts it, so there is no endpoint to ping. 864 installs a week from pypi. Last commit 23 Oct 2026.

Official PDF.co MCP server: convert, merge, split, OCR, search and fill PDFs through the PDF.co API

Installs per day peak 392 · avg 42 · +496% w/w

a month agotoday

864

Installs / week

pypi · pdfco-mcp

Stars

0 open issues

23 Oct 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

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

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.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add pdfco-mcp -e 'X_API_KEY=<X_API_KEY>' -- uvx pdfco-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pdfco-mcp": {
      "command": "uvx",
      "args": [
        "pdfco-mcp"
      ],
      "env": {
        "X_API_KEY": "<X_API_KEY>"
      }
    }
  }
}

~/.codex/config.toml

[mcp_servers.pdfco-mcp]
command = "uvx"
args = ["pdfco-mcp"]
env = { X_API_KEY = "<X_API_KEY>" }

.cursor/mcp.json

{
  "mcpServers": {
    "pdfco-mcp": {
      "command": "uvx",
      "args": [
        "pdfco-mcp"
      ],
      "env": {
        "X_API_KEY": "<X_API_KEY>"
      }
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "pdfco-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pdfco-mcp"
      ],
      "env": {
        "X_API_KEY": "<X_API_KEY>"
      }
    }
  }
}

Put your own value in place of <X_API_KEY> (Your PDF.co API key (from https://app.pdf.co)). The author’s registry entry marks it as required.

Alternatives to PDF.co

same job, measured the same way

PDFBetter

by pdfbetter

Fill, convert, OCR, merge, split, extract data from and summarize PDFs. AI answers cite the page.

answering

Papyrio PDF Tools

by atabekdemurtaza

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

233 installs/wk local only

PDF Toolkit MCP

by eigencharlie

Unofficial PDF toolkit (merge/split/compress/OCR/convert/watermark/protect/...) via iLoveAPI.

14 installs/wk local only

SmartPDF

by smartpdf

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

48 tools answering

PDF Suite MCP

by beepboop2025

37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.

local only

PDF Toolkit

by tensormaster

Convert PDFs/images to Word, Excel, and Markdown. Split, merge, and watermark PDF files.

answering

Huoshui PDF Converter

by huoshuiai42

An MCP server that provides PDF file conversion

92 installs/wk local only

conv2pdf

by conv2pdf

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

33 installs/wk local only

PDF.co — questions

Answers built from our own checks of this server.

Why is there no uptime for PDF.co?

PDF.co 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 pypi package pdfco-mcp was installed 864 times last week.

How do I connect PDF.co?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls pdfco-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use PDF.co?

The pypi package pdfco-mcp was installed 864 times in the last week. Week over week that is +496%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is PDF.co open source?

Yes — it is published under the MIT licence, written in Python and 9 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.