Native PDF renderer for AI markdown. Cover, TOC, page-numbered footer. Fonts embedded, zero config.
io.github.mrslbt/pdf-it MCP Server
This Model Context Protocol (MCP) server provides a native PDF renderer for AI-generated Markdown. It supports cover generation, a table of contents (TOC), and a page-numbered footer, with fonts embedded. It includes an MCP server and a Claude Code skill.
🛠️ Key Features
Native PDF rendering for AI Markdown
Cover page support
Table of contents (TOC)
Page-numbered footer
Embedded fonts
Requires zero config
🚀 Use Cases
Converting AI Markdown output into PDFs with structured sections (TOC)
Producing document-style exports with a cover and consistent footers
Integrating with Claude Code workflows via the provided skill
⚡ Developer Benefits
Native rendering and embedded fonts
MCP server integration under the Model Context Protocol
Development alignment via documented topics (mcp-server, pdf-generator)
⚠️ Limitations
Description excerpt ends mid-sentence (“turns ”), so additional behavior is not specified in the provided source data.
A Model Context Protocol (MCP) server and Claude Code skill that turns markdown into PDFs that look like they were made on purpose. Cover page, table of contents, code blocks that hold across page breaks, page-numbered footer. One command from your Claude session to a file you can send to a client.
Fonts ship inside the package, so every PDF looks the same on every machine. Nothing to install, nothing to configure.
Why this exists
Every Claude Code research session ends the same way: a wall of useful markdown and no clean way to turn it into a PDF a person would actually want to read.
Chrome print: takes 30 seconds, output looks like a Word doc. Manual HTML conversion: 10 minutes per document. Pandoc: works but defaults look like a 2008 academic paper. None of it produces an artifact you would send to a client.
pdf-it is one command. The output is designed by default.
pdf-it body example
Install
bash
npm install -g pdf-it-mcp
Or run on demand with npx pdf-it-mcp.
Requirements
Node.js 20 or newer
Nothing else to install. The renderer and fonts ship inside the package.
Add to ~/.cursor/mcp.json with the same shape as Claude Desktop.
Cline / Continue / Zed / Goose
Standard MCP config. Same npx -y pdf-it-mcp command.
Use
In any Claude session connected to the server, ask:
Save this as a PDF
Or any of these phrasings: export as PDF, make a PDF report from this, turn this into a PDF, /pdf. The skill picks up the request and routes it through pdf-it. The output lands in ~/Documents/pdf-it/ by default.
Tools
Tool
Description
generate_pdf
Convert markdown into a PDF. Accepts a template (research-report or plain), optional title and author for the cover, and an optional output path.
list_templates
Return the list of available templates with descriptions.
generate_pdf parameters
Parameter
Required
Description
content
yes
Markdown string to convert
title
no
Shown on the cover and in the page footer
author
no
Shown on the cover above the date
output_path
no
Absolute path for the output. Defaults to ~/Documents/pdf-it/{slug}-{timestamp}.pdf
template
no
research-report (default) or plain
Templates
Name
Description
research-report
Cover page with title, author, and date. Auto-generated table of contents from H1 and H2 headings. Body with proper hierarchy. Footer with title and page number. Best for research, summaries, design docs, reports.
plain
No cover, no TOC. Dense body content only. Best for short notes and quick exports.
Skill
This package ships with a Claude Code skill at SKILL.md. Trigger phrases the skill responds to:
By default PDFs are written to ~/Documents/pdf-it/{slug}-{timestamp}.pdf. Pass output_path to override.
Design
Three families ship inside the package:
Newsreader for the cover title (display 60, light) and body H1 (display 32). High-contrast serif that holds editorial weight at large sizes.
DM Sans for H2, H3, table type, and the TOC heading. Quieter sub-hierarchy.
JetBrains Mono for page numbers, metadata, code, and figure captions.
Pure white paper, near-black ink (#111113), secondary ink for date and table cells (#2B2B2E), muted gray for page numbers and date (#7A7A7E), hairline borders (#E6E6E6). No accent colors. Code blocks render without syntax highlighting on purpose: color choices in PDFs age badly.
Every value lives in src/templates/design-tokens.ts as the single source of truth. If you want a different design language, fork the components. They live in src/templates/components/ and are plain React-PDF components with a small surface area.
How it works
Parse: remark converts your markdown into an AST.
Compose: the AST becomes typed React components (Cover, TOC, and body primitives like H1/H2/H3, Paragraph, CodeBlock, Blockquote, Table, lists, and charts).
Render:@react-pdf/renderer rasterizes the React tree into a deterministic PDF with embedded fonts and TOC anchors.
Output: the PDF lands in ~/Documents/pdf-it/{slug}-{timestamp}.pdf with title/author metadata embedded.
Total time: typically sub-second for a 5-page document, 1-2 seconds for a 30-page document.
This 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.
pdf-it runs locally and ships its own renderer (@react-pdf/renderer) and fonts. Use at your own risk. The author accepts no liability for issues arising from misuse, prompt injection, bugs, or rendering failures.
