MCP.so
Sign In

Aleph-10: Vector Memory MCP Server

@bjkemp

Repository

About Aleph-10: Vector Memory MCP Server

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

#mathgpt#math-solver#math-assistant

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Aleph-10: Vector Memory MCP Server?

Aleph-10: Vector Memory MCP Server is a Model Context Protocol server that combines weather data retrieval from the National Weather Service API with vector‑based semantic memory storage. It is intended for developers who need an MCP‑compatible server for both weather information and persistent, searchable memory via embeddings.

How to use Aleph-10: Vector Memory MCP Server?

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.

Key features of Aleph-10: Vector Memory MCP Server

  • 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

Use cases of Aleph-10: Vector Memory MCP Server

  • Fetching live weather alerts for any US state during an MCP session
  • Obtaining weather forecasts for given latitude/longitude coordinates
  • Storing conversational context as vector embeddings for later retrieval
  • Searching for semantically similar text entries across stored memories
  • Updating or deleting individual memory entries by ID

FAQ from Aleph-10: Vector Memory MCP Server

What are the prerequisites to run the server?

Node.js 18.x or higher and the pnpm package manager are required.

How do I configure the embedding provider?

Set the environment variable EMBEDDING_PROVIDER to gemini or ollama. If using Gemini, provide a GEMINI_API_KEY. For Ollama, set OLLAMA_BASE_URL (default: http://localhost:11434).

Where is the vector database stored?

The vector database is stored at the path specified by VECTOR_DB_PATH, which defaults to ./data/vector_db.

What weather data source is used?

Weather data is sourced from the National Weather Service API.

Can I run embeddings locally without an internet connection?

Yes, by setting EMBEDDING_PROVIDER to ollama and running a local Ollama instance.

Frequently asked questions

What are the prerequisites to run the server?

Node.js 18.x or higher and the pnpm package manager are required.

How do I configure the embedding provider?

Set the environment variable `EMBEDDING_PROVIDER` to `gemini` or `ollama`. If using Gemini, provide a `GEMINI_API_KEY`. For Ollama, set `OLLAMA_BASE_URL` (default: `http://localhost:11434`).

Where is the vector database stored?

The vector database is stored at the path specified by `VECTOR_DB_PATH`, which defaults to `./data/vector_db`.

What weather data source is used?

Weather data is sourced from the National Weather Service API.

Can I run embeddings locally without an internet connection?

Yes, by setting `EMBEDDING_PROVIDER` to `ollama` and running a local Ollama instance.

Comments

Basic information

Category

Memory & Knowledge

Transports

stdio

Author

bjkemp

More Memory & Knowledge MCP servers

Anytype MCP Server

anyproto

An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.

467

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2

Obsidian MCP Server

StevenStavrakis

A simple MCP server for Obsidian

717

Basic Memory

basicmachines-co

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

3.4K

PLUR

plur-ai

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

226