Skip to content
appsgit

Mnemosyne

Mnemosyne is an MCP server that adds database tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Evidence-tracked local memory MCP server: one SQLite file; corrections retire dependent memories. It has 161 GitHub stars, is released under the MIT license and runs locally with npx -y mnemosy-ai.

github.com/28naem-del/mnemosyne (opens in a new tab)

Data as of from the GitHub API and the official MCP registry; description from the project's repository. Report an error

Install Mnemosyne

Generated from the server's MCP registry entry. Replace your-value with your own values.

Claude Desktop

claude_desktop_config.json
{
  "mcpServers": {
    "mnemosyne": {
      "command": "npx",
      "args": [
        "-y",
        "mnemosy-ai"
      ],
      "env": {
        "MNEMOSYNE_INDEX_MODE": "your-value"
      }
    }
  }
}

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

Claude Code

claude mcp add --env MNEMOSYNE_INDEX_MODE=your-value --transport stdio mnemosyne -- npx -y mnemosy-ai

Cursor

.cursor/mcp.json
{
  "mcpServers": {
    "mnemosyne": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mnemosy-ai"
      ],
      "env": {
        "MNEMOSYNE_INDEX_MODE": "your-value"
      }
    }
  }
}

Project file; use ~/.cursor/mcp.json to enable it in every project.

VS Code

.vscode/mcp.json
{
  "servers": {
    "mnemosyne": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mnemosy-ai"
      ],
      "env": {
        "MNEMOSYNE_INDEX_MODE": "your-value"
      }
    }
  }
}

Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).

Environment variables

Variables the server reads at startup.

NameRequiredDescription
MNEMOSYNE_INDEX_MODENoDense index used for semantic recall; defaults to auto

About Mnemosyne

Mnemosyne is local-first, long-term memory for AI agents: one SQLite file that keeps what an agent learned together with the evidence it came from, served to any host over TypeScript, MCP, CLI or HTTP. When a source is corrected, the memories recorded as depending on it are retired, so the next agent starts from what current recorded evidence still supports instead of repeating a stale lesson. The local engine needs no model API key, database server or Docker.

  • ai-agents
  • llm
  • memory
  • typescript
  • model-context-protocol
  • sqlite
  • agent-memory
  • claude-code
  • cursor
  • llm-memory

FAQ

Mnemosyne FAQ

Still curious? Email info@appsgit.com.

How do I install the Mnemosyne MCP server?

Add the command npx -y mnemosy-ai to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.

Is Mnemosyne free?

The server is open source under the MIT license, so running it is free. It does not declare any required API key.

Is Mnemosyne actively maintained?

The most recent commit was on Nov 10, 2026. The latest release is v2.0.0, published Oct 27, 2026. appsgit only lists MCP servers with a commit in the last six months.