# Simple Memory Extension MCP Server

> An MCP server to extend the context of agents. Useful when coding big features or vibe coding and need to store/recall progress, key moments or changes or anything worth remembering. Simply ask the agent to store memories and recall whenever you want.

- **Type:** MCP server
- **Install:** `agentstack add mcp-gmacev-simple-memory-extension-mcp-server`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [gmacev](https://agentstack.voostack.com/s/gmacev)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [gmacev](https://github.com/gmacev)
- **Source:** https://github.com/gmacev/Simple-Memory-Extension-MCP-Server

## Install

```sh
agentstack add mcp-gmacev-simple-memory-extension-mcp-server
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Simple Memory Extension MCP Server

An MCP server to extend the context window / memory of agents. Useful when coding big features or vibe coding and need to store/recall progress, key moments or changes or anything worth remembering. Simply ask the agent to store memories and recall whenever you need or ask the agent to fully manage its memory (through cursor rules for example) however it sees fit.

## Usage

### Starting the Server

```bash
npm install
npm start
```

### MCP setup

```json
  "mcpServers": {
    "simple-memory": {
      "url": "http://localhost:3000/sse",
      "trust": false
    }
  }
```

### Available Tools

#### Context Item Management
- `store_context_item` - Store a value with key in namespace
- `retrieve_context_item_by_key` - Get value by key
- `delete_context_item` - Delete key-value pair

#### Namespace Management
- `create_namespace` - Create new namespace
- `delete_namespace` - Delete namespace and all contents
- `list_namespaces` - List all namespaces
- `list_context_item_keys` - List keys in a namespace

#### Semantic Search
- `retrieve_context_items_by_semantic_search` - Find items by meaning

### Semantic Search Implementation

1. Query converted to vector using E5 model
2. Text automatically split into chunks for better matching
3. Cosine similarity calculated between query and stored chunks
4. Results filtered by threshold and sorted by similarity
5. Top matches returned with full item values

## Development

```bash
# Dev server
npm run dev

# Format code
npm run format
```

## .env

```
# Path to SQLite database file
DB_PATH=./data/context.db

PORT=3000

# Use HTTP SSE or Stdio
USE_HTTP_SSE=true

# Logging Configuration: debug, info, warn, error
LOG_LEVEL=info
```

## Semantic Search

This project includes semantic search capabilities using the E5 embedding model from Hugging Face. This allows you to find context items based on their meaning rather than just exact key matches.

### Setup

The semantic search feature requires Python dependencies, but these *should be* automatically installed when you run: `npm run start`

### Embedding Model

We use the [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct)

### Notes

Developed mostly while vibe coding, so don't expect much :D. But it works, and I found it helpful so w/e. Feel free to contribute or suggest improvements.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [gmacev](https://github.com/gmacev)
- **Source:** [gmacev/Simple-Memory-Extension-MCP-Server](https://github.com/gmacev/Simple-Memory-Extension-MCP-Server)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-gmacev-simple-memory-extension-mcp-server
- Seller: https://agentstack.voostack.com/s/gmacev
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.