Aleph-10: Vector Memory MCP Server

by bjkemp

187 downloads
Not rated
GitHub

About

Vector Memory MCP Server - An MCP server with vector-based memory storage capabilities

Details

Author
bjkemp
Downloads
187
Categories
Knowledge Base

- Retrieves weather alerts and forecasts via the National Weather Service API
- Stores and retrieves information using semantic vector search
- Supports both Google Gemini (cloud) and Ollama (local) embedding providers
- Allows metadata to be attached and filtered on memory entries

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:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Aleph-10: Vector Memory MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Node.js 18+, pnpm, clone the repository, run pnpm install, configure environment variables in a .env file, then pnpm build and start with node build/index.js. The server exposes tools such as get‑alerts, get‑forecast, memory‑store, memory‑retrieve, memory‑update, memory‑delete, and memory‑stats.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "aleph-10: vector memory mcp server": {
            "aleph-10": {
                "command": "node",
                "args": [
                    "build/index.js"
                ]
            }
        }
    }
}

McpServers

{
    "aleph-10": {
        "command": "node",
        "args": [
            "build/index.js"
        ]
    }
}

Aleph-10: Vector Memory MCP Server

Aleph-10 is a Model Context Protocol (MCP) server that combines weather data services with vector-based memory storage. This project provides tools for retrieving weather information and managing semantic memory through vector embeddings.

Features

- Weather Information: Get weather alerts and forecasts using the National Weather Service API
- Vector Memory: Store and retrieve information using semantic search
- Multiple Embedding Options: Support for both cloud-based (Google Gemini) and local (Ollama) embedding providers
- Metadata Support: Add and filter by metadata for efficient memory management

Getting Started

Prerequisites

- Node.js 18.x or higher
- pnpm package manager

Installation

1. Clone the repository

git clone https://github.com/yourusername/aleph-10.git
cd aleph-10

2. Install dependencies

pnpm install

3. Configure environment variables (create a .env file in the project root)

EMBEDDING_PROVIDER=gemini
GEMINI_API_KEY=your_gemini_api_key
VECTOR_DB_PATH=./data/vector_db
LOG_LEVEL=info

4. Build the project

pnpm build

5. Run the server

node build/index.js

Usage

The server implements the Model Context Protocol and provides the following tools:

Weather Tools

- get-alerts: Get weather alerts for a specific US state
- Parameters: state (two-letter state code)

- get-forecast: Get weather forecast for a location
- Parameters: latitude and longitude

Memory Tools

- memory-store: Store information in the vector database
- Parameters: text (content to store), metadata (optional associated data)

- memory-retrieve: Find semantically similar information
- Parameters: query (search text), limit (max results), filters (metadata filters)

- memory-update: Update existing memory entries
- Parameters: id (memory ID), text (new content), metadata (updated metadata)

- memory-delete: Remove entries from the database
- Parameters: id (memory ID to delete)

- memory-stats: Get statistics about the memory store
- Parameters: none

Configuration

The following environment variables can be configured:

| Variable | Description | Default |
|----------|-------------|---------|
| EMBEDDING_PROVIDER | Provider for vector embeddings (gemini or ollama) | gemini |
| GEMINI_API_KEY | API key for Google Gemini | - |
| OLLAMA_BASE_URL | Base URL for Ollama API | http://localhost:11434 |
| VECTOR_DB_PATH | Storage location for vector database | ./data/vector_db |
| LOG_LEVEL | Logging verbosity | info |

Development

Project Structure

The project follows a modular structure:

aleph-10/
├── src/                         # Source code
│   ├── index.ts                 # Main application entry point
│   ├── weather/                 # Weather service module
│   ├── memory/                  # Memory management module
│   ├── utils/                   # Shared utilities
│   └── types/                   # TypeScript type definitions
├── tests/                       # Test files
└── vitest.config.ts             # Vitest configuration

Running Tests

The project uses Vitest for testing. Run tests with:

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.