gitSERVER - MCP Server for README Management

A Model Context Protocol server for managing README files in development projects.

Overview

gitSERVER is a FastMCP-based server that streamlines README file management through the Model Context Protocol. It provides automated README creation, content generation, summarization, and MCP client integration.

Features

• Automatic README file creation when files do not exist
• Content management with append functionality
• README content summarization and analysis
• MCP resource integration for content access
• Intelligent prompt generation for README analysis
• Robust error handling with fallback mechanisms

Installation

Prerequisites

• Python 3.7 or higher
• FastMCP library

Setup Steps

1. Install dependency: pip install fastmcp
2. Save main.py to your project directory
3. Start the server: python main.py

Usage

MCP Tools

create_file(response: str)

• Purpose: Generate and append content to README file
• Parameter: response (string) - content to add to README
• Returns: Confirmation message
• Use case: Adding structured documentation content

sumamrize_readme()

• Purpose: Read complete README file content
• Parameters: None
• Returns: Full README content or empty file message
• Use case: Content review and analysis

MCP Resources

README://content

• Provides direct access to README file content
• Uses MCP resource access pattern
• Allows MCP clients to fetch README content

MCP Prompts

readme_summary()

• Generates prompts for README summarization
• Returns contextual prompt or empty file message
• Detects empty files automatically

Project Structure

your-project/ main.py (MCP server implementation) README.md (Auto-generated README file) other-files (Your project files)

How It Works

File Management

1. Detects existing README.md files in project directory
2. Creates empty README.md if none exists
3. Safely appends new content while preserving existing data
4. Ensures all file operations complete successfully

MCP Integration

• Tools: Direct function calls for README operations
• Resources: Resource-based README content access
• Prompts: Contextual prompt generation for AI interactions

Technical Details

File Operations

• Safe file handling with proper open/close operations
• Content stripping to remove unnecessary whitespace
• Fallback messages for empty or missing files

Error Handling

• Creates README.md automatically when needed
• Returns user-friendly messages for empty content
• Handles file operation exceptions gracefully

API Reference

Tool Functions:

• create_file(response): Append content to README
• sumamrize_readme(): Retrieve README content

Resource Endpoints:

• README://content: Direct README content access

Prompt Generators:

• readme_summary(): Context-aware README summarization

Use Cases

• Documentation automation and maintenance
• README content analysis for improvements
• New project setup with proper documentation
• MCP workflow integration for README management

Development

Contributing

1. Fork the repository
2. Create feature branch
3. Implement changes
4. Test with MCP clients
5. Submit pull request

Testing Requirements

Test that your MCP client can:

• Call create_file tool successfully
• Retrieve content via sumamrize_readme
• Access README://content resource
• Generate prompts with readme_summary

Compatibility

• MCP Protocol: Standard MCP client compatible
• Python: Requires version 3.7 or higher
• Dependencies: Only requires FastMCP library

License

Open source project. Check repository for license details.

Support

For issues or questions:

• Check project repository for existing issues
• Create new issues for bugs or features
• Refer to FastMCP documentation for MCP questions

Note: This is a Model Context Protocol server. You need an MCP-compatible client to interact with the server effectively.

Google Gemini PDF Chatbot

A Streamlit web application for uploading PDF documents and asking questions about their content using Google Gemini AI.

Overview

This chatbot application uses Google Gemini 1.5 Flash model to provide intelligent question-answering for uploaded PDF documents. Users upload PDF files, the app processes content, and allows questions about the document.

Features

• PDF Upload Support: Upload and process PDF documents
• Text Extraction: Automatically extracts text from PDF files
• Intelligent Chunking: Splits large documents into manageable chunks
• AI-Powered Q&A: Uses Google Gemini 1.5 Flash for accurate answers
• Interactive Web Interface: Clean Streamlit interface
• Real-time Processing: Instant responses to user queries

Installation

Prerequisites

• Python 3.7 or higher
• Google API key for Gemini AI
• Required Python packages

Setup Instructions

1. Clone repository and navigate to project directory

2. Install dependencies: pip install streamlit python-dotenv PyPDF2 langchain langchain-google-genai

3. Create .env file in project root: GOOGLE_API_KEY=your_google_api_key_here

4. Get Google API Key:

   • Visit Google AI Studio or Google Cloud Console
   • Create or select project
   • Enable Gemini API
   • Generate API key and add to .env file

Usage

Running the Application

1. Start Streamlit app: streamlit run app.py

2. Access application:

   • Open web browser
   • Navigate to http://localhost:8501

Using the Chatbot

1. Upload Document:

   • Click file uploader
   • Select PDF file
   • Wait for processing

2. Ask Questions:

   • Type question in text input field
   • Press Enter
   • AI analyzes document and provides answer

Supported File Types

• PDF files (.pdf) - Fully implemented
• Text files (.txt) - Declared support
• Word documents (.docx) - Declared support

Technical Architecture

Core Components

1. Streamlit Frontend: Web interface for uploads and interaction
2. PDF Processing: PyPDF2 extracts text from documents
3. Text Chunking: LangChain CharacterTextSplitter breaks large texts
4. AI Integration: Connects to Google Gemini via LangChain
5. Question Answering: LangChain QA chain for document-based answers

Processing Flow

1. User uploads PDF document
2. Application extracts text from all pages
3. Text split into chunks (1000 chars with 200 char overlap)
4. Chunks converted to LangChain Document objects
5. User submits question
6. QA chain processes question against document chunks
7. Gemini AI generates and returns answer

Configuration

Environment Variables

• GOOGLE_API_KEY: Your Google API key for Gemini AI services

Text Splitter Settings

• Chunk Size: 1000 characters
• Chunk Overlap: 200 characters
• Separator: Newline character

AI Model Configuration

• Model: Google Gemini 1.5 Flash
• Chain Type: stuff (processes all chunks together)

Project Structure

project/ app.py (Main Streamlit application) .env (Environment variables - not in repo) requirements.txt (Python dependencies) README.md (Project documentation)

Dependencies

Required Python Packages:

• streamlit: Web application framework
• python-dotenv: Environment variable management
• PyPDF2: PDF text extraction
• langchain: AI application framework
• langchain-google-genai: Google Gemini integration

Installation: pip install streamlit python-dotenv PyPDF2 langchain langchain-google-genai

Troubleshooting

Common Issues

1. API Key Errors:

   • Ensure Google API key is correctly set in .env file
   • Verify API key has access to Gemini AI services

2. PDF Processing Issues:

   • Some PDFs may have text as images (not supported)
   • Encrypted PDFs may require additional handling

3. Memory Issues:

   • Large PDF files may consume significant memory
   • Consider file size limits for production use

Error Handling

Application includes error handling for:

• Missing text content in PDF pages
• API key configuration issues
• File upload validation

Contributing

1. Fork the repository
2. Create feature branch
3. Make changes
4. Test with various PDF files
5. Commit changes
6. Push to branch
7. Create Pull Request

License

Open source project. Check LICENSE file for details.

Acknowledgments

• Google AI for Gemini AI model
• LangChain team for AI application framework
• Streamlit team for web app framework

Support

For issues or questions:

• Create issue in project repository
• Check existing documentation first
• Provide detailed environment and issue information

Note: Requires valid Google API key and internet connection. Ensure proper permissions for Google Gemini AI services. This is a Python-based web application built with Streamlit that allows users to input a song name and artist name, fetch the lyrics using the Genius API, and then analyze the meaning of those lyrics using Google's Gemini AI model.

The project consists of three main files:

1. app.py - The main Streamlit application that provides the user interface
2. genius_lyrics.py - Handles fetching lyrics from the Genius API using the lyricsgenius library
3. lyrics_meaning.py - Uses Google's Gemini AI to provide detailed line-by-line analysis of the lyrics

Key features:

• Clean, intuitive web interface with song search functionality
• Integration with Genius API for accurate lyrics retrieval
• AI-powered analysis using Google's Gemini 2.5 Flash model for deep lyric interpretation
• Expandable lyrics viewer with download option to save lyrics as text files
• Streaming AI analysis for better user experience
• Error handling for missing lyrics and API failures
• Session state management to maintain data across interactions

The application requires API keys for both Genius and Google's Gemini AI service, which should be stored in environment variables. Users can search for any song, view the complete lyrics, download them, and get detailed AI analysis explaining metaphors, cultural references, and emotional meanings.