Newsletter Generator
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Newsletter GeneratorGenerate a newsletter about quantum computing breakthroughs."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI-Powered Newsletter Generator (MCP)
1. Project Overview
This project is an AI-powered newsletter generation system built using the Model Context Protocol (MCP). It dynamically creates structured newsletters covering 8 distinct sections and provides automated NLP analytics (word count, reading time, sentiment, and keywords).
2. Architecture Explanation
The project is built on Node.js and uses the MCP SDK. It exposes two core tools:
generate_newsletter: Uses OpenAI's API to dynamically write content based on structured prompt templates.analyze_newsletter: Uses local processing to parse the generated markdown, calculate word frequencies, estimate reading time, and score sentiment.
The MCP Server runs over stdio, allowing it to be integrated easily into local LLM clients like Claude Desktop, or run standalone via the CLI.
3. Prerequisites
Node.js (v18 or higher)
npm or yarn
OpenAI API Key (optional but recommended for actual text generation)
4. Installation Steps
Clone the repository or extract the files.
Open your terminal in the project root.
Run
npm installto install the MCP SDK and dotenv.
5. Environment Variable Setup
Copy
.env.exampleand rename it to.env.Open
.envand paste your OpenAI API key:OPENAI_API_KEY=sk-your-real-key-here
6. How to Start the MCP Server
To start the raw MCP server (which communicates via standard input/output):
npm start(Note: Because it uses stdio, it will appear to hang. This is normal, as it is waiting for JSON-RPC messages. Press Ctrl+C to exit).
7. How to Generate Newsletter & 8. Run Analytics via CLI
To use the application manually as a standard Node app:
npm run cliFollow the on-screen prompts to enter a topic. It will automatically generate the newsletter, save it to the /outputs folder, and print out analytics (saving the JSON to /analytics).
9. Example CLI Commands
npm install
npm run cli
# Topic: Quantum Computing in AI10. How to Use with Claude (MCP Integration)
To use this server as a tool inside Claude Desktop:
Open your Claude Desktop configuration file (e.g.,
claude_desktop_config.json).Add the following entry to your
mcpServersblock:{ "mcpServers": { "newsletter-generator": { "command": "node", "args": ["/absolute/path/to/ai-newsletter-mcp/server/index.js"] } } }Restart Claude Desktop.
Ask Claude: "Please generate a newsletter about Agentic Workflows using the generate_newsletter tool, and then analyze the result."
11. Future Improvements (For Final Year Project)
Database Integration: Connect MongoDB or PostgreSQL to track user historical generated newsletters and trends over time.
Advanced NLP: Replace heuristic sentiment analysis with a local HuggingFace model or an LLM call.
Web UI: Build a React.js or Next.js frontend to visualize the analytics using charting libraries like Recharts or Chart.js.
Email Dispatch: Integrate SendGrid or Nodemailer to automatically email the generated newsletter to a list of subscribers.
12. Automated Scheduling & Email Delivery
The project includes an automated workflow that generates, analyzes, and emails newsletters without manual intervention.
📧 Email Configuration
This system uses nodemailer. To send emails (e.g., via Gmail):
Go to your Google Account > Security.
Enable 2-Step Verification.
Search for "App Passwords" and generate a new password for this app.
Add the credentials to your
.envfile:EMAIL_USER=your-email@gmail.com EMAIL_PASS=your-16-char-app-password
(Security Note: Never commit your .env file or actual password to GitHub!)
⏰ Scheduler Configuration
Edit the config/schedulerConfig.json file to manage delivery:
Demo Mode (Every 5 minutes):
{ "mode": "interval", "intervalMinutes": 5 }Production Mode (Daily at 8:00 AM):
{ "mode": "daily", "dailyTime": "08:00" }🚀 How to Run the Scheduler
The scheduler boots up automatically when the MCP server runs. However, to run the scheduler independently for testing:
npm run scheduler📋 Logging & Common Errors
All automated actions are logged inside the /logs directory.
SMTP Authentication Error: Check that you are using a Google App Password and not your standard login password.
Empty Output: Ensure your
OPENAI_API_KEYis valid.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/raya2912/MCP-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server