Gemini Context MCP Server

🚀 Venus Context MCP Server

A powerful implementation of the MCP (Model Context Protocol) server that leverages Gemini's capabilities for context management and caching. This server fully utilizes Gemini's 2M token context window and provides tools for efficiently caching large contexts.

🚀 Quick Start

This server is a powerful implementation of the MCP (Model Context Protocol), leveraging Gemini's capabilities for context management and caching. It fully utilizes Gemini's 2M token context window and provides tools for efficiently caching large contexts.

✨ Features

Context Management

• Support for up to 2M token context window - Fully utilize Gemini's powerful context capabilities.
• Session-based conversations - Maintain session state across multiple interactions.
• Intelligent context tracking - Add, retrieve, and search for context using metadata.
• Semantic similarity search - Match based on semantic relevance of context content.
• Dynamic context updates - Automatically adjust context based on conversation history.

API Caching

• Large context caching - Provide efficient context storage and retrieval for long text generation tasks.
• Adaptive caching strategy - Manage the cache intelligently based on access frequency and time.
• Cache persistence options - Support persisting important contexts to local or remote storage.
• Batch operation support - Provide batch processing capabilities for multiple context records.
• Context version control - Effectively manage and trace different versions of contexts.

📦 Installation

1. Clone the repository:

git clone https://github.com/yourusername/gemini-context-mcp.git
cd gemini-context-mcp

2. Install dependencies:

npm install

3. Configure environment variables and create a .env file:

GEMINI_API_KEY=your_api_key_here
GEMINI_MODEL=gemini-2.0-flash

# Optional - Model settings
GEMINI_TEMPERATURE=0.7
GEMINI_TOP_K=40
GEMINI_TOP_P=0.9
GEMINI_MAX_OUTPUT_TOKENS=2097152

# Optional - Server settings
MAX_SESSIONS=50
SESSION_TIMEOUT_MINUTES=120
MAX_MESSAGE_LENGTH=1000000
MAX_TOKENS_PER_SESSION=2097152
DEBUG=false

4. Start the server:

node dist/index.js

📄 License

MIT