MCP Synaptic
About
Memory-enhanced MCP server with local RAG database and expiring memory capabilities
Details
- Author
- jvanmelckebeke
- Downloads
- 235
- Categories
- Knowledge Base
Jump to
- Expiring memories with configurable TTL and automatic cleanup
- Support for ephemeral, short-term, long-term, and permanent memory types
- Optional Redis backend for distributed memory storage
- ChromaDB-based vector database with semantic search
- API-based or local embedding models (sentence-transformers)
- Full MCP protocol, SSE, and WebSocket real-time communication
- Docker-ready with multi-service orchestration
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP SynapticCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Python 3.11+ and the UV package manager. Run uv sync to install dependencies, then uv run mcp-synaptic init to initialize the project and uv run mcp-synaptic server to start the server on http://localhost:8000. For containerized deployment, use docker-compose up --build. Configuration is managed through environment variables (see .env.example).
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp synaptic": {
"mcp-synaptic": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}McpServers
{
"mcp-synaptic": {
"command": "uv",
"args": [
"sync"
]
}
}MCP Synaptic
A memory-enhanced MCP (Model Context Protocol) server with local RAG (Retrieval-Augmented Generation) database and expiring memory capabilities.
Features
🧠 Memory Management
- Expiring Memories: Store temporary memories with configurable TTL (Time To Live) - Memory Types: Support for different memory categories (short-term, long-term, ephemeral) - Automatic Cleanup: Background processes to remove expired memories - Redis Integration: Optional Redis backend for distributed memory storage📚 RAG Database
- Local Vector Storage: ChromaDB-based vector database for document storage - Embedding Models: Built-in support for sentence-transformers models - Semantic Search: Similarity-based document retrieval - Document Management: Add, update, and delete documents with versioning🔄 Real-time Communication
- Server-Sent Events (SSE): Real-time updates for memory and RAG operations - MCP Protocol: Full Model Context Protocol implementation - WebSocket Support: Alternative real-time communication channel - Event Streaming: Live updates for memory expiration and document changes🐳 Docker Ready
- Containerized Deployment: Ready-to-use Docker containers - Docker Compose: Multi-service orchestration with Redis and database - Environment Configuration: Flexible configuration through environment variablesQuick Start
Prerequisites
- Python 3.11 or higher
- UV package manager
- Docker (optional, for containerized deployment)
Installation
1. Clone the repository:
git clone https://github.com/your-org/mcp-synaptic.git
cd mcp-synaptic
2. Install dependencies:
# For API-based embeddings (recommended - lightweight)
uv sync
# For local embeddings (includes PyTorch - heavy)
uv sync --extra local-embeddings
3. Initialize the project:
uv run mcp-synaptic init
4. Start the server:
uv run mcp-synaptic server
The server will start on http://localhost:8000 by default.
Docker Deployment
1. Build and run with Docker Compose:
docker-compose up --build
2. Or run individual container:
docker build -t mcp-synaptic .
docker run -p 8000:8000 mcp-synaptic
Configuration
Environment Variables
Create a .env file in the project root (use .env.example as template):
```env
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
