MCP.so
Sign In

MCP Server: Memory

@kwanLeeFrmVi

Repository

About MCP Server: Memory

No overview available yet

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Server: Memory?

MCP Server: Memory is an MCP (Model Context Protocol) server that provides persistent memory capabilities for AI models through a local knowledge graph. It is derived from the original @modelcontextprotocol/server-memory package and acts as a bridge between an AI model (such as Claude) and a locally stored knowledge graph, enabling the model to retain and recall information across interactions.

How to use MCP Server: Memory?

The server is primarily used with MCP-compatible clients like Claude Desktop. Configure it in the client’s settings under mcpServers, specifying the npx command with the package name mcp-server-memory. Optionally set the MEMORY_FILE_PATH environment variable to customize the location of the knowledge graph file.

Key features of MCP Server: Memory

  • 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
  • Persistent storage in a local JSON file

Use cases of MCP Server: Memory

  • Enabling an AI assistant to remember user preferences and history across sessions
  • Building a personal knowledge base that an AI can query and update
  • Creating a collaborative memory store where multiple interactions accumulate facts
  • Providing context for long-running conversations or multi-step tasks

FAQ from MCP Server: Memory

What does MCP Server: Memory do?

It implements the Model Context Protocol to give AI models persistent memory via a knowledge graph. The model can create entities, define relationships, store observations, and search for information across interactions.

How is this different from the original @modelcontextprotocol/server-memory?

This package is a modified version of the original server, tailored for the author’s specific needs. The README does not provide further details on differences.

What are the runtime requirements?

The server runs via npx, which requires Node.js. The package is published on npm. No other dependencies are explicitly mentioned.

Where is the knowledge graph data stored?

By default, the knowledge graph is stored in a knowledge_graph.json file in the current working directory. You can override the path using the MEMORY_FILE_PATH environment variable.

Does the server support authentication or transport security?

The README does not mention any authentication or transport security mechanisms.

Frequently asked questions

What does MCP Server: Memory do?

It implements the Model Context Protocol to give AI models persistent memory via a knowledge graph. The model can create entities, define relationships, store observations, and search for information across interactions.

How is this different from the original `@modelcontextprotocol/server-memory`?

This package is a modified version of the original server, tailored for the author’s specific needs. The README does not provide further details on differences.

What are the runtime requirements?

The server runs via `npx`, which requires Node.js. The package is published on npm. No other dependencies are explicitly mentioned.

Where is the knowledge graph data stored?

By default, the knowledge graph is stored in a `knowledge_graph.json` file in the current working directory. You can override the path using the `MEMORY_FILE_PATH` environment variable.

Does the server support authentication or transport security?

The README does not mention any authentication or transport security mechanisms.

Comments

Basic information

Category

Memory & Knowledge

License

MIT license

Transports

stdio

Author

kwanLeeFrmVi

More Memory & Knowledge MCP servers

Tempreon

Tempreon

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

Context Portal MCP (ConPort)

GreatScottyMac

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

763

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

1

Agimem

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

Solomd

zhitongblog

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

425