MCP.so
Sign In

MCP OpenMemory Server

@baryhuang

Basic information

Category

Other

License

MIT

Transports

stdio

Author

baryhuang

About MCP OpenMemory Server

Simple standalone MCP server giving Claude the ability to remember your conversations and learn from them over time.

MCP OpenMemory Server config

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

{
  "mcpServers": {
    "mcp-openmemory": {
      "command": "npx",
      "args": [
        "@peakmojo/mcp-openmemory@latest"
      ]
    }
  }
}

MCP OpenMemory Server tools

4

Save individual conversation messages to memory storage. Use this when you want to persist important parts of our current conversation. Call this for each significant message or exchange that should be remembered for future conversations. Typically used during or at the end of conversations to store key information, decisions, or context.

Retrieve the current memory abstract that summarizes past conversations and context. Use this at the beginning of conversations to understand what has been discussed before, or when you need to check existing memory context. This gives you the processed summary of previous interactions, not raw messages. Call this to "remember" previous conversations with this user.

Save a new or updated memory abstract after processing recent conversations. Use this when you have reviewed recent messages, combined them with existing memory context, and created an improved summary. The typical workflow is: 1) Get current memory abstract, 2) Get recent memories, 3) Process and combine them, 4) Save the updated abstract here. This maintains the evolving memory summary over time.

Retrieve recent raw conversation messages from the last few days. Use this when you need to see actual conversation history rather than the processed summary. Helpful for creating or updating memory abstracts, or when you need specific details from recent exchanges. This gives you the unprocessed message data to work with.

Overview

What is MCP OpenMemory Server?

MCP OpenMemory Server is an MCP (Model Context Protocol) server that gives Claude the ability to remember conversations and learn from them over time. It uses SQLite for persistent local storage without external dependencies.

How to use MCP OpenMemory Server?

Configure the server in Claude Desktop’s claude_desktop_config.json using npx with the package @peakmojo/mcp-openmemory@latest, setting the environment variable MEMORY_DB_PATH to a persistent absolute path. The server starts automatically when Claude Desktop is launched and creates the database on first use. Four tools become available: save_memory, recall_memory_abstract, update_memory_abstract, and get_recent_memories.

Key features of MCP OpenMemory Server

  • Store and recall individual conversation messages.
  • Maintain summarized memory context across conversations.
  • Access recent conversations within configurable time windows.
  • Uses SQLite for persistent storage without external dependencies.
  • Supports memory namespacing by project via separate databases or a “context” field.

Use cases of MCP OpenMemory Server

  • Preserve user preferences and working style across multiple Claude sessions.
  • Maintain ongoing project status and context without re-explaining each time.
  • Keep a searchable log of key decisions and their rationale for recurring tasks.
  • Separate memory per project (e.g., one database for Claude, another for Cursor).

Frequently asked questions

1

What happens if I don’t set `MEMORY_DB_PATH`?

The database defaults to `./memory.sqlite` in a temporary location that may be cleared when Claude Desktop restarts, causing loss of conversation history.

2

What runtime does MCP OpenMemory Server require?

It requires Node.js to run the MCP server. Verify installation with `node --version`.

3

Where does the conversation data live?

All data is stored locally in a SQLite database file at the path specified by `MEMORY_DB_PATH`. No external cloud storage is used.

4

Does the server support semantic search over memories?

No, semantic search is not yet supported. Memory retrieval is currently based on stored summaries and recent history.

5

How are MCP OpenMemory Server’s tools accessed?

Claude Desktop exposes four tools after configuration: `save_memory`, `recall_memory_abstract`, `update_memory_abstract`, and `get_recent_memories`. They appear in the tools list when clicking the slider icon (🔧) in the input box.

Comments

More Other MCP servers