Sentiment Analysis Server

Python Gradio MCP MIT License

🌟 Overview

MCP Sentiment Analysis Server is a cutting-edge, robust sentiment analysis solution built on the Model Context Protocol (MCP). This powerful server provides real-time sentiment analysis capabilities with seamless integration into AI workflows and applications.

graph TD
    A[📝 Input Text] --> B[🔍 MCP Server]
    B --> C[🧠 Sentiment Engine]
    C --> D[📊 Analysis Results]
    D --> E[🎯 Confidence Score]
    D --> F[😊 Emotion Classification]
    D --> G[📈 Detailed Metrics]
    
    style A fill:#e1f5fe
    style B fill:#f3e5f5
    style C fill:#fff3e0
    style D fill:#e8f5e8
    style E fill:#fff8e1
    style F fill:#fce4ec
    style G fill:#f1f8e9

✨ Key Features

🎨 Advanced Capabilities

• 🎭 Multi-dimensional Analysis: Emotion, polarity, and intensity detection
• 📈 Batch Processing: Handle multiple texts simultaneously
• 🔄 Real-time Streaming: Live sentiment monitoring
• 🎚️ Confidence Scoring: Reliability metrics for each analysis
• 🌍 Multi-language Support: Global sentiment understanding
• 📱 RESTful API: Easy integration with any platform

🚀 Quick Start

# Clone the repository
git clone https://github.com/AdilzhanB/MCP_sentiment_analysis_server.git
cd MCP_sentiment_analysis_server

# Install dependencies
pip install -r requirements.txt

# Or using conda
conda env create -f environment.yml
conda activate mcp-sentiment

# config.py
SENTIMENT_CONFIG = {
    "model": "transformers",
    "confidence_threshold": 0.7,
    "batch_size": 32,
    "max_length": 512,
    "enable_gpu": True
}

# Set environment variables
export MCP_SENTIMENT_PORT=8080
export MCP_SENTIMENT_HOST=localhost

# Start the MCP server
python app.py

# Or with custom configuration
python app.py --config custom_config.yaml --port 8080

💻 Usage Examples

🐍 Python Integration

from mcp_sentiment import SentimentAnalyzer

# Initialize the analyzer
analyzer = SentimentAnalyzer()

# Analyze single text
result = analyzer.analyze("I love this amazing product!")
print(f"Sentiment: {result.sentiment}")
print(f"Confidence: {result.confidence:.2f}")
print(f"Emotions: {result.emotions}")

# Batch analysis
texts = ["Great service!", "Could be better", "Absolutely fantastic!"]
results = analyzer.batch_analyze(texts)

🌐 REST API Usage

# Single analysis
curl -X POST http://localhost:8080/analyze \
  -H "Content-Type: application/json" \
  -d '{"text": "This is an amazing experience!"}'

# Batch analysis
curl -X POST http://localhost:8080/batch-analyze \
  -H "Content-Type: application/json" \
  -d '{"texts": ["Good product", "Bad service", "Excellent quality"]}'

🤖 MCP Client Integration

import { MCPClient } from "@modelcontextprotocol/sdk";

const client = new MCPClient({
  name: "sentiment-analyzer",
  version: "1.0.0"
});

const response = await client.request({
  method: "sentiment/analyze",
  params: {
    text: "I'm excited about this new feature!",
    options: {
      detailed: true,
      emotions: true
    }
  }
});

📊 Performance Metrics

gantt
    title Sentiment Analysis Performance Timeline
    dateFormat  X
    axisFormat %s
    
    section Processing
    Text Preprocessing    :0, 10
    Model Inference      :10, 35
    Post-processing      :35, 45
    Response Generation  :45, 50
    
    section Quality Gates
    Confidence Check     :20, 30
    Validation          :40, 48

🔧 Configuration

📋 Environment Variables

# Server Configuration
MCP_SENTIMENT_HOST=localhost
MCP_SENTIMENT_PORT=8080
MCP_SENTIMENT_DEBUG=false

# Model Configuration
SENTIMENT_MODEL_PATH=./models/sentiment
SENTIMENT_BATCH_SIZE=32
SENTIMENT_MAX_LENGTH=512

# Performance Tuning
ENABLE_GPU=true
NUM_WORKERS=4
CACHE_SIZE=1000

# Security
API_KEY_REQUIRED=true
RATE_LIMIT_PER_MINUTE=100

⚡ Advanced Settings

sentiment_model:
  name: "roberta-sentiment-advanced"
  version: "1.2.0"
  parameters:
    max_sequence_length: 512
    batch_size: 32
    confidence_threshold: 0.75
    
emotion_model:
  enabled: true
  categories: ["joy", "anger", "fear", "sadness", "surprise", "disgust"]
  threshold: 0.6
  
preprocessing:
  clean_text: true
  handle_emojis: true
  normalize_case: true
  remove_noise: true

📈 Monitoring & Analytics

📊 Real-time Dashboard

• 🔥 Real-time Metrics: Request volume, response times, error rates
• 📈 Sentiment Trends: Historical analysis and patterns
• 🎯 Accuracy Tracking: Model performance monitoring
• ⚡ Performance Insights: Resource utilization and optimization

🚨 Health Checks

# Health endpoint
curl http://localhost:8080/health

# Detailed status
curl http://localhost:8080/status/detailed

# Metrics endpoint
curl http://localhost:8080/metrics

🧪 Testing

🔬 Running Tests

# Run all tests
pytest tests/ -v

# Run with coverage
pytest tests/ --cov=src --cov-report=html

# Performance tests
pytest tests/performance/ -v --benchmark-only

# Integration tests
pytest tests/integration/ -v

📋 Test Coverage

🚀 Deployment

🐳 Docker Deployment

FROM python:3.9-slim

WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt

COPY . .
EXPOSE 8080

CMD ["python", "app.py"]

# Build and run
docker build -t mcp-sentiment .
docker run -p 8080:8080 mcp-sentiment

☁️ Cloud Deployment

# docker-compose.yml
version: '3.8'
services:
  mcp-sentiment:
    build: .
    ports:
      - "8080:8080"
    environment:
      - MCP_SENTIMENT_HOST=0.0.0.0
      - ENABLE_GPU=false
    deploy:
      resources:
        limits:
          memory: 1G
        reservations:
          memory: 512M

🤝 Contributing

📋 Contribution Guidelines

1. 🍴 Fork the repository
2. 🌿 Create a feature branch (git checkout -b feature/amazing-feature)
3. 💻 Code your contribution
4. 🧪 Test thoroughly
5. 📝 Commit your changes (git commit -m 'Add amazing feature')
6. 🚀 Push to the branch (git push origin feature/amazing-feature)
7. 🎯 Open a Pull Request

🏆 Contributors Hall of Fame

📚 Documentation

📖 Comprehensive Guides

• 🚀 Quick Start Guide - Get up and running in minutes
• 🔧 API Reference - Complete API documentation
• 🏗️ Architecture Guide - System design and components
• ⚙️ Configuration Manual - Detailed setup instructions
• 🧪 Testing Guide - Testing strategies and examples
• 🚀 Deployment Guide - Production deployment strategies

🆘 Support & Community

🎯 Support Channels

• 💬 Community Chat: Real-time help and discussions
• 📧 Email Support: [email protected]
• 🐛 Bug Reports: Use GitHub Issues
• 💡 Feature Requests: GitHub Discussions
• 📚 Documentation: Comprehensive guides and tutorials

📜 License

🙏 Acknowledgments

• 🤖 Hugging Face - For the amazing transformer models
• 🎨 Gradio Team - For the beautiful web interface framework
• 🔧 MCP Community - For the Model Context Protocol standard
• 💝 Contributors - For making this project amazing
• 🌍 Open Source Community - For the continuous inspiration

🚀 Ready to Get Started?

Get Started View Demo Star Repository

---

Made with ❤️ by Adilzhan Baidalin