pdf-it

Name: pdf-it
Author: mrslbt

@mrslbt

リポジトリホームページ

pdf-it について

Native PDF renderer for AI-generated markdown. Cover page, auto TOC, page-numbered footer. Fonts embedded, zero config.

#mcp #pdf #claude-code #claude-desktop #cursor #anthropic-skill #markdown #pdf-generator #markdown-to-pdf #ai-agents #puppeteer

基本情報

カテゴリ

ファイルとストレージ

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

mrslbt

投稿者

Marsel Bait

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

ツール

Convert markdown into a PDF. Accepts a template (`research-report` or `plain`), optional title and author for the cover, and an optional output path.

Return the list of available templates with descriptions.

概要

What is pdf-it?

pdf-it is a Model Context Protocol (MCP) server and Claude Code skill that converts markdown into PDFs with a professional appearance—cover page, table of contents, code blocks that hold across page breaks, and page-numbered footer. Fonts are embedded in the package, so every PDF looks identical on any machine with no extra dependencies. It is designed for users of Claude Desktop, Claude Code, and other MCP-compatible hosts who want to turn markdown output into client-ready PDFs in a single command.

How to use pdf-it?

Install globally with npm install -g pdf-it-mcp or run on demand with npx pdf-it-mcp. Configure the MCP server in your client (e.g., Claude Desktop, Claude Code, Cursor) using the command npx -y pdf-it-mcp. In a Claude session, trigger the skill with phrases like “save this as PDF”, “export as PDF”, “make a PDF report from this”, or “/pdf”. The PDF is written to ~/Documents/pdf-it/{slug}-{timestamp}.pdf by default.

Key features of pdf-it

Converts markdown to PDF with one command
Ships with embedded fonts for consistent output across machines
Two templates: research-report (cover, TOC) and plain (no cover, no TOC)
Auto-generated cover page, table of contents, and page-numbered footer
Highly structured output using React-PDF components
Output lands in ~/Documents/pdf-it/ by default

Use cases of pdf-it

Exporting a Claude Code research session as a professional PDF report
Turning markdown notes into client-ready design documents or summaries
Generating consistent PDF reports from markdown without manual formatting
Quickly converting short notes into dense, no-frills PDFs

FAQ from pdf-it

What are the runtime requirements for pdf-it?

Node.js 20 or newer is required. No other dependencies are needed—the renderer and fonts are bundled inside the package.

Where does pdf-it save the generated PDFs?

By default, PDFs are saved to ~/Documents/pdf-it/{slug}-{timestamp}.pdf. You can override the output path with the output_path parameter.

What templates are available in pdf-it?

Two templates are available: research-report (default) includes a cover page with title, author, and date, an auto-generated table of contents, and a footer with title and page number. plain omits the cover and TOC for dense body content only.

Is pdf-it affiliated with Anthropic?

No. pdf-it is an unofficial, community-built tool. It is not affiliated with, endorsed by, or sponsored by Anthropic PBC. Claude and Claude Code are trademarks of Anthropic PBC.

How does pdf-it render PDFs?

It parses markdown into an AST using remark, composes the AST into React-PDF components (Cover, TOC, body primitives), and renders the React tree into a deterministic PDF using @react-pdf/renderer with embedded fonts and TOC anchors.