KEPTA — the memory for AI systems MCP Server

by damiantodorovicio.github.DamianTodorovic/keptav3.1.2

Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.

2Node.jsstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active1d ago

Install KEPTA — the memory for AI systems MCP server

claude mcp add kepta -- npx -y kepta-mcp

{
  "mcpServers": {
    "kepta": {
      "command": "npx",
      "args": [
        "-y",
        "kepta-mcp"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "kepta": {
      "command": "npx",
      "args": [
        "-y",
        "kepta-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "kepta": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "kepta-mcp"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "kepta": {
      "command": "npx",
      "args": [
        "-y",
        "kepta-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Active — last maintenance signal 1d ago. The newest of the signals below sets the band.

›How do I install the KEPTA — the memory for AI systems MCP server in Claude Code?

Run: claude mcp add kepta -- npx -y kepta-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does KEPTA — the memory for AI systems require an API key?

No required environment variables are declared in its published metadata.

›Can I use KEPTA — the memory for AI systems as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is KEPTA — the memory for AI systems in the official MCP registry?

Yes, as io.github.DamianTodorovic/kepta.

Other memory MCP servers.