mcp server

auto-blogger

Automatic Blog Writer (Powered by AOAI and uv)

rkttu/auto-bloggercommunitylistedunreviewed

Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

uv (`curl -LsSf https://astral.sh/uv/install.sh | sh`)

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

{
  "mcpServers": {
    "auto-blogger": {
      "command": "uvx",
      "args": [
        "auto-blogger"
      ]
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 26, 2026

Auto-Blogger

AI-powered blog post generator CLI tool with MCP integration, SEO optimization, and Unsplash images.

🌟 Generate high-quality, SEO-optimized blog posts with automatic research, keywords, and professional images!

✨ Key Features

🤖 LangChain-powered blog post generation with customizable tone and length
🔍 MCP (Model Context Protocol) integration for automatic research from trusted sources
🎯 SEO Optimization: Auto-generates keywords, abstract, and URL-friendly slugs
📸 Unsplash Integration: Automatically adds professional header images with proper attribution
📝 YAML Front Matter: Includes metadata (title, date, author, keywords, abstract)
🌍 Multi-language Support: Korean, English, and more
🔌 OpenAI-compatible APIs: Works with Azure OpenAI, OpenRouter, vLLM, LiteLLM, etc.
💻 Cross-platform: Wrapper scripts for Linux, macOS, and Windows
🎨 Markdown Linter Compliant: Clean, properly formatted markdown output

🚀 Quick Start

Prerequisites

Python 3.12 or higher
UV package manager
OpenAI API key (or compatible service)

Installation

# Clone the repository
git clone https://github.com/rkttu/auto-blogger.git
cd auto-blogger

# Install dependencies with UV
uv sync

# Initialize configuration
uv run auto-blogger init

Basic Usage

# Generate a blog post (default: 1 Unsplash image, Korean)
uv run auto-blogger generate "Your Topic Here"

# Save to file with custom options
uv run auto-blogger generate "AI in 2024" \
  --output ai-trends.md \
  --language English \
  --length long \
  --research

⚙️ Configuration

Initialize configuration:
```
uv run auto-blogger init
```

Edit .env file with your credentials:

# OpenAI Configuration
OPENAI_API_KEY=your-api-key-here
DEFAULT_MODEL=gpt-4o-mini
OPENAI_API_BASE=  # Optional: for Azure OpenAI or compatible services

# Blog Settings
DEFAULT_LANGUAGE=Korean
DEFAULT_TONE=professional
DEFAULT_LENGTH=medium
TEMPERATURE=0.7

# MCP Servers (optional, for research)
MCP_SERVERS=https://learn.microsoft.com/api/mcp

# Unsplash API (optional, for images)
UNSPLASH_APPLICATION_ID=your-app-id
UNSPLASH_ACCESS_KEY=your-access-key
UNSPLASH_SECRET_KEY=your-secret-key

📖 Usage Examples

Generate with Images

# With 1 image (default)
uv run auto-blogger generate "Docker Best Practices"

# With multiple images
uv run auto-blogger generate "Cloud Architecture" --image-count 2

# Without images
uv run auto-blogger generate "API Design" --image-count 0

Research Mode

# Gather reference materials from MCP servers
uv run auto-blogger generate "Kubernetes Security" \
  --research \
  --tone technical \
  --output k8s-security.md

Multi-language Support

# Korean (default)
uv run auto-blogger generate "인공지능의 미래"

# English
uv run auto-blogger generate "The Future of AI" --language English

Custom Tone and Length

# Technical, long-form article
uv run auto-blogger generate "Distributed Systems" \
  --tone technical \
  --length long

# Casual, short post
uv run auto-blogger generate "Weekend Coding Projects" \
  --tone casual \
  --length short

CLI Options

Options:
  --output, -o PATH       Output file path (default: stdout)
  --language, -l TEXT     Language (default: Korean)
  --tone, -t TEXT         Tone: professional, casual, technical
  --length TEXT           Length: short (300-500), medium (800-1200), long (1500-2500)
  --research, -r          Enable MCP research
  --author, -a TEXT       Author name (default: Auto-Blogger)
  --image-count, -i INT   Number of images (0-3, default: 1)
  --help                  Show help message

🎯 Features in Detail

SEO Optimization

Auto-Blogger automatically generates:

Keywords: 5-8 relevant SEO keywords extracted from content
Abstract: 2-3 sentence marketing-friendly summary
URL Slug: English-friendly slug (even for non-English titles)

MCP Integration

Leverage Model Context Protocol servers for research:

Microsoft Learn documentation
Custom MCP servers
Automatic reference gathering and citation

Unsplash Images

Professional images with:

Keyword-based search
Proper attribution (required by Unsplash)
Download tracking (API compliance)
Markdown-ready formatting

Output Format

---
title: "Your Title"
date: 2024-11-20
author: Auto-Blogger
language: English
slug: your-title-slug
keywords:
  - keyword1
  - keyword2
abstract: |
  Your auto-generated abstract here.
---

![Photo by Photographer on Unsplash](image-url)

*Photo by [Photographer](link) on [Unsplash](link)*

> This article was written with partial assistance from generative AI.

# Your Title

[Content here...]

💖 Support This Project

If Auto-Blogger helps you create better content faster, please consider:

⭐ Star this repository on GitHub
🐛 Report issues or suggest new features
🔀 Contribute via pull requests
💝 Sponsor via GitHub Sponsors

Your support helps maintain and improve this project. Every contribution, big or small, makes a difference!

🛠️ Development️ Development

# Install dependencies
uv sync

# Run locally
uv run auto-blogger generate "Test Topic"

# Run tests (if available)
uv run pytest

🗺️ Roadmap

🤝 Contributing

Contributions are welcome! Please feel free to submit issues and pull requests.

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

📄 License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

🙏 Acknowledgments

Built with LangChain
Images from Unsplash
Research powered by Model Context Protocol

Made with ❤️ by rkttu

If this project helps you, please consider sponsoring ⭐