mcpField
M
MCP Server: Memory

MCP Server: Memory

Local
github.com/kwanLeeFrmViMemory & Knowledge2Updated 82w ago
Repository

About MCP Server: Memory

MCP Server: Memory provides persistent AI memory through a locally stored knowledge graph. It is for MCP-compatible clients that need to create, connect, update, search, and retrieve facts about entities across interactions.

Key features

  1. 01Persistent local knowledge graph
  2. 02Create and manage entities
  3. 03Define entity relationships
  4. 04Store observations and facts
  5. 05Search and retrieve graph information

Use cases

  1. 01Recall facts across conversations
  2. 02Connect people, places, and concepts
  3. 03Store observations for later retrieval

MCP support

The MCP server exposes knowledge-graph memory operations to MCP clients, including entity and relationship management, observation storage, and search.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "memory-kwanleefrmvi": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-memory"
      ],
      "env": {
        "MEMORY_FILE_PATH": "<MEMORY_FILE_PATH>"
      }
    }
  }
}
Run commandnpx -y mcp-server-memory
Environment variables to set
MEMORY_FILE_PATH

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-server-memory

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Server: Memory

NPM Version Bun Version License

This project is derived from the original @modelcontextprotocol/server-memory package, modified for my specific needs.

An MCP (Model Context Protocol) server providing persistent memory capabilities for AI models through a knowledge graph. This allows models like Claude to retain and recall information across interactions.

Overview

This server implements the Model Context Protocol and acts as a bridge between an AI model and a persistent knowledge graph stored locally. It allows the model to:

  • Create and manage entities (people, places, concepts, etc.).
  • Define relationships between entities.
  • Store observations or facts associated with entities.
  • Search and retrieve information from the knowledge graph.

By default, the knowledge graph is stored in a knowledge_graph.json file in the current working directory where the server is run.

Usage with Claude Desktop

This server is primarily designed to be used with MCP-compatible clients like the Claude Desktop application. You configure it within the client's settings.

Example mcpServers Configuration:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "mcp-server-memory"],
      "env": {
        "MEMORY_FILE_PATH": "/path/to/your/custom_memory.json"
      }
    }
  }
}

...[rest of existing content remains unchanged...]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.