zmem MCP Memory Server

Name: zmem MCP Memory Server
Author: meetdhanani17

@meetdhanani17

リポジトリ

zmem MCP Memory Server について

Global MCP server that manage all the project data,

#typescript #ai #mcp #vscode #cursor #windsurf #mcp-server

基本情報

カテゴリ

メモリとナレッジ

ランタイム

node

トランスポート

stdio

公開者

meetdhanani17

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": {
    "zmem": {
      "command": "npx",
      "args": [
        "ts-node",
        "index.ts"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is zmem MCP Memory Server?

zmem MCP Memory Server is a TypeScript-based Model Context Protocol (MCP) server that enables project-specific and knowledge graph-based memory for Claude, LLM agents, and other tools. It supports storing, retrieving, and managing entities, relations, and observations per project, with a focus on flexibility and cross-project knowledge sharing.

How to use zmem MCP Memory Server?

To use zmem, add it to your MCP configuration (e.g., for Windsurf) with the command and path to the built index. Install dependencies, build, and run via npm or Docker. Use the MCP client to call tools such as save_project_observations with a project ID and observations. Persisted memory files are stored in a configurable directory (default /app/memories).

Key features of zmem MCP Memory Server

Knowledge graph storage for entities, relations, and observations
CRUD operations via MCP tools
Persistence to disk (memory.json)
Docker and TypeScript support
Cross-project knowledge sharing and migration
Scalable, disk-persistent, queryable memory for agent ecosystems

Use cases of zmem MCP Memory Server

Agents and LLMs storing and retrieving structured memory per project.
Cross-project knowledge sharing and migration.
Building scalable, disk-persistent, and queryable memory for agent ecosystems.

FAQ from zmem MCP Memory Server

What MCP tools does zmem expose?

It exposes tools for saving and getting project observations, adding graph observations, creating entities and relations, deleting entities/observations/relations, reading the graph, searching nodes, searching all projects, opening nodes, and copying memory.

Where are memories stored?

Memories are persisted to disk in a memories directory (configurable via the MEMORY_DIR_PATH environment variable, default /app/memories).

Does zmem support Docker?

Yes. Build the Docker image with docker build -t zmem-mcp-server and run it with a volume mount to persist memories.

How do I save observations for a project?

Call the save_project_observations tool via the MCP API with a projectId and an array of observations, each containing an entityName and contents array.

What runtime does zmem require?

zmem is TypeScript-based and requires Node.js. Install dependencies with npm install, build with npm run build, and run with npm start for production.