広告掲載
MCP.so
ログイン

Simple Memory Extension MCP Server

@gmacev

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

トランスポート

stdio

作者

gmacev

Simple Memory Extension MCP Server について

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.

Simple Memory Extension MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "simple-memory": {
      "type": "http",
      "url": "http://localhost:3000/sse"
    }
  }
}

Simple Memory Extension MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。

概要

What is Simple Memory Extension MCP Server?

An MCP server that extends the context window / memory of AI agents by letting them store and recall progress, key moments, changes, or any noteworthy information. It is designed for developers working on large features or “vibe coding” who need persistent memory across sessions.

How to use Simple Memory Extension MCP Server?

Install with npm install, then start with npm start. Configure the MCP client by adding "simple-memory" to mcpServers with "url": "http://localhost:3000/sse" and "trust": false. Set environment variables like DB_PATH, PORT, USE_HTTP_SSE, and LOG_LEVEL in a .env file. Use the provided tools to store, retrieve, delete context items, manage namespaces, and perform semantic searches.

Key features of Simple Memory Extension MCP Server

  • Store key-value pairs within named namespaces
  • Retrieve items by exact key or by semantic search
  • Create, delete, and list namespaces
  • Semantic search using E5 embedding model
  • SQLite database for persistent storage

Use cases of Simple Memory Extension MCP Server

  • Remember coding progress and decisions during large feature work
  • Let the agent manage its own memory via Cursor rules
  • Recall specific changes or key moments from past sessions
  • Find context items by meaning rather than by key name

よくある質問

1

What database does the server use?

It uses SQLite, with the database file path configured via the `DB_PATH` environment variable (default `./data/context.db`).

2

How does semantic search work?

Queries are converted to vectors using the E5 embedding model (`intfloat/multilingual-e5-large-instruct`). Text is chunked for better matching, cosine similarity is computed, results are filtered by a threshold and sorted by similarity, and the top matches are returned.

3

Does it require Python?

Yes. The semantic search feature requires Python dependencies, which are automatically installed when you run `npm start`.

4

What transport protocols are supported?

The server supports HTTP SSE (Server‑Sent Events) by default (`USE_HTTP_SSE=true`). It also supports stdio when `USE_HTTP_SSE=false`.

5

How do I set up the server in my MCP client?

Add a `"simple-memory"` entry to `mcpServers` with `"url": "http://localhost:3000/sse"` and `"trust": false`. Adjust the port if you change the `PORT` environment variable.

コメント

「メモリとナレッジ」の他のコンテンツ

LoreKeeper RPG (lorekeeper.com)

LoreKeeper Ltd

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

Code Graph Rag

vitali87

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

5.3K

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

Snipara

alopez3006

MCP connector for Snipara, the Project Brain for AI coding agents

1
広告掲載