🌌 STRATA — Universal Context Bridge

STRATA is a high-performance Model Context Protocol (MCP) server that serves as a Universal Context Bridge for AI assistants and LLM agents (Claude Desktop, Cursor, Continue.dev, ChatGPT, etc.).

It gives AI models persistent memory across conversations and coding sessions, backed by Supabase PostgreSQL, full-text indexing, and pgvector semantic search.

---

⚡ Features

• 🧠 Persistent Context Memory: AI agents can save decisions, design systems, API contracts, preferences, and code snippets across sessions.
• 🔍 Intelligent Memory Search: Fast full-text and contextual search with automatic recency fallbacks.
• 🚀 Modern MCP 2.0 SDK: Built using the latest MCPServer decorator architecture with Server-Sent Events (SSE) streaming transport.
• 🗄️ Supabase & PostgreSQL: Battle-tested cloud database layer with pgvector support and Row-Level Security (RLS).
• 🔄 Singleton Connection Pooling: Cached client instances for high-throughput, low-latency tool execution.
• 🩺 Built-in Health Checks: REST endpoints for uptime monitoring and connectivity status (/health).

---

🛠️ Available MCP Tools

Tool	Description	Parameters
save_memory	Save context, preferences, decisions, or code into long-term memory	content (str), title (opt), tags (opt)
search_memory	Search past context and discussions matching keywords or queries	query (str), limit (int, default: 5)
list_memories	List recent context entries stored in STRATA	limit (int, default: 10)
delete_memory	Remove a specific memory entry by UUID	memory_id (str)
get_stats	View database connection status, memory count, and metadata	None

---

🚀 Quick Start

1. Prerequisites

• Python 3.10 or higher
• A Supabase account & project

2. Clone & Setup Environment

# Clone the repository
git clone https://github.com/your-username/STRATA.git
cd STRATA

# Copy environment file and configure your keys
cp .env.example .env

Edit .env with your Supabase credentials:

SUPABASE_URL=https://your-project.supabase.co
SUPABASE_KEY=your-supabase-service-role-key
DEFAULT_USER_ID=your-user-uuid (optional)

3. Install Dependencies

cd apps/api
python -m venv venv

# Activate virtual environment:
# Windows (PowerShell):
.\venv\Scripts\Activate.ps1
# macOS / Linux:
source venv/bin/activate

# Install requirements
pip install -r requirements.txt

4. Database Setup

Run the SQL schema located in supabase_schema.sql in your Supabase SQL Editor to initialize the tables, vector extensions, and full-text indexes.

5. Start the Server

# From apps/api directory:
uvicorn main:app --reload --port 8000

The server starts on http://localhost:8000 with the following endpoints:

• SSE Endpoint: http://localhost:8000/sse
• Messages Endpoint: http://localhost:8000/messages/
• Health Check: http://localhost:8000/health

---

🔌 Connecting to MCP Clients

Claude Desktop

Add this to your claude_desktop_config.json:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "strata": {
      "url": "http://localhost:8000/sse"
    }
  }
}

Cursor IDE

In Cursor settings under Features > MCP Servers, add a new server:

• Name: STRATA
• Type: sse
• URL: http://localhost:8000/sse

---

📁 Project Structure

STRATA/
├── apps/
│   └── api/                   # Python MCP Server
│       ├── main.py            # Server logic, MCPServer instance & tools
│       ├── requirements.txt   # Python dependencies
│       └── venv/              # Python virtual environment
├── .env.example               # Template environment file
├── .gitignore                 # Version control ignores
├── package.json               # Root monorepo configuration
├── supabase_schema.sql        # Database schema, pgvector, and indexes
└── README.md                  # Documentation

---

🛡️ License

MIT License. See LICENSE for details. #� �b�o�u�n�c�e�-�m�c�p� � �