NanoPDF MCP Server is a Model Context Protocol (MCP) implementation that brings AI-powered PDF editing and generation capabilities directly to Claude Desktop. It enables users to modify existing PDF pages or generate new ones using Google's Gemini 3 Pro model, all within a privacy-focused local environment.

🛠️ Key Features

AI-Driven Editing: Modify PDF slides using natural language prompts.
Smart Generation: Create new, visually consistent slides after any page.
Local Privacy: Operates in a privacy-focused, local environment.
Gemini Pro Integration: Leverages Google's Gemini 3 Pro model for tasks.

🚀 Use Cases

Edit and annotate PDFs via plain-language requests.
Generate new slides that match the surrounding design.
Produce consistent, publication-ready PDF content locally.

⚡ Developer Benefits

MCP-compliant server for seamless integration with Claude Desktop.
Clear, text-based prompts for editing and generation workflows.
Local processing reduces data exposure in cloud-only setups.

⚠️ Limitations

Details on supported file complexity and model prompts are limited in the readme excerpt.

NanoPDF MCP Server

🚀 Key Features

AI-Driven Editing: Modify PDF slides using natural language prompts.
Smart Generation: Create new, visually consistent slides after any page.
Visual Previews: View specific PDF pages as high-quality images.
Privacy First: All versioning and temporary files are stored locally on your machine.
State Preservation: Uses Tesseract OCR to maintain searchable text layers in AI-generated pages.
Version Control: Built-in undo functionality for safe experimentation.

📋 Prerequisites

System Dependencies

The server requires poppler (for PDF rendering) and tesseract (for OCR) installed on your system.

macOS (Homebrew):
bash
```
brew install poppler tesseract
```

Ubuntu/Debian:

bash

sudo apt-get install poppler-utils tesseract-ocr

Environment Variables

A Google Gemini API key is required to power the AI features.

GEMINI_API_KEY: Your Google AI Studio API key.

🛠️ Installation & Setup

1. Development Environment

This project uses uv for lightning-fast Python package management.

bash

# Navigate to the server directory
cd mcp-server

# Install dependencies
uv sync

2. Configure Claude Desktop

Add the NanoPDF server to your Claude Desktop configuration:

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

json

{
  "mcpServers": {
    "nanopdf": {
      "command": "/Users/username/.local/bin/uv", # replace with your uv path
      "args": [
        "run",
        "--directory",
        "/Users/username/nano-pdf-mcp/mcp-server", # replace with your mcp-server path
        "server.py"
      ]
    }
  }
}

IMPORTANT

Change username to your actual macOS username. Ensure the --directory path is the absolute path to your mcp-server folder.

📖 Usage Guide

For detailed tool descriptions and workflow examples, please refer to the Usage Guide.

Core Workflow

Open PDF: open_pdf(pdf_path="/path/to/document.pdf")
Edit/Add: edit_pdf_page(session_id="...", page_number=1, prompt="...")

📂 Project Structure

mcp-server/: Core MCP server implementation.
- server.py: Main entry point and tool definitions.
- mcp_pdf_utils.py: PDF processing, OCR, and rendering logic.
- mcp_ai_utils.py: Gemini Pro Vision API integration.
- history_manager.py: Local session and version history tracker.
- output/: Local storage for sessions and previews.
LICENSE: Project license (MIT).
USAGE.md: Detailed usage instructions and examples.

🤝 Acknowledgements

Based on the original NanoPDF project. Adapted for the Model Context Protocol.

📄 License

MIT License

NanoPDF