titen-memory

Titen Memory is an MCP server focused on Developer tools and Data & databases: Agent memory with no API key, no LLM, and no embedding provider. Serves MCP over stdio against a local SQLite store, or Cloudflare Workers + D1. Drop-in for @modelcontextprotocol/server-memory; every memory keeps its source, its scope, and the evidence th.

It is published on npm as titen-memory and hosted on GitHub at ramaaditya49/titen (16 GitHub stars, 207 weekly npm downloads, last repository push on 2026-10-19). Based on its public metadata, its operational scope includes: reads local files, connects to outside service api, requires api key or token.

Run titen-memory with --ignore-scripts in claude_desktop_config.json or .cursor/mcp.json:

{
  "mcpServers": {
    "titen-memory": {
      "command": "npx",
      "args": ["-y", "--ignore-scripts", "titen-memory"]
    }
  }
}

• Local file read access: Reads local documents or database files. Point it only at the specific files needed for the task so sensitive workspace files remain out of reach.
• External API & account scope: Connects to third-party service APIs. Use a dedicated, least-privilege token scoped only to the workspaces or repositories this tool needs.
• Credential & token exposure: Requires API keys or secrets in configuration. Store credentials in environment variables with read-only or minimum required scopes and rotate them regularly.
• Dependency & version pinning: Distributed via npm (titen-memory). Pin an exact release version or commit SHA rather than floating tags so upstream updates are reviewed first.