MCP Memory Server

mcp-memory-server

javascript

2

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "stevenwangler-mcp-memory-server": {
      "command": "npx",
      "args": [
        "mcp-server-memory"
      ]
    }
  }
}

MCP Memory Server provides a persistent, knowledge-graph based memory layer for Large Language Models. It stores entities and relationships, enables semantic search, and maintains memory across sessions so your models can reason with context over time.

How to use

You use the memory server by running it as a local/portable process and configuring your MCP clients to connect to it. The server offers persistent memory with CRUD operations for memory items, semantic search to find relevant information, and cross-session memory so conversations can reference prior context. Start the server locally and point your MCP client to the local process, then perform memory operations such as creating entities, linking relationships, retrieving memory by semantic similarity, and updating or deleting records as needed.

How to install

Prerequisites: you need Node.js and npm installed on your machine.

Install dependencies.
Build the project.
Run the server.

Additional sections

Development and testing workflows are supported through an inspector tool that helps you start a proxy server, launch a web interface, and obtain a session token for testing.

Integration with MCP clients follows the standard approach: provide the MCP server as a configured endpoint in your client setup. A typical local runtime uses the npm binary to run the server.

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["mcp-server-memory"]
    }
  }
}

Available tools

Knowledge Graph Storage

Persistent graph-based memory store for entities and relationships that can be queried and updated over time.

Entity Management

Create, update, and relate entities to model memory concepts and data.

Semantic Search

Find memory items using semantic similarity to user queries or prompts.

Cross-session Memory

Maintain context across different conversations and sessions for consistent reasoning.

Memory Operations

Full CRUD operations to manage memory resources and their metadata.