Works with Claude Desktop, Claude Code, Cursor and any Model Context Protocol client. Runs on your own machine, or hosted with no install.
mcp-pdf is an MCP project maintained in the theluckystrike/mcp-pdf repository. The maintainer describes its purpose as “Works with Claude Desktop, Claude Code, Cursor and any Model Context Protocol client. Runs on your own machine, or hosted with no install”. Read the project documentation for the complete scope.
The project provides a local client configuration using node. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| 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… |
| 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) |
{
"mcpServers": {
"pdf": {
"command": "node",
"args": [
"/absolute/path/to/mcp-pdf/dist/index.js"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
EU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents.
Paid AI utilities for web comparison, code checks, document extraction, security, and research.
Browse, generate and import Abyssale designs — banners, video, PDF — from your AI client.
MCP server with tools to search, fetch, analyze, and report on scientific papers and datasets.
Autonomous WCAG 2.1 accessibility auditor that scans, fixes, re-verifies, and generates VPAT 2.5 EN 301 549 reports using AI vision analysis + DOM scanning.