memorylane

memorylane is a MCP server by deusXmachina-dev that desktop app that captures screen activity, stores AI summaries and OCR text locally, and exposes the history via semantic search and a timeline.

Updated 2026-10-17

What is memorylane?

memorylane is a MCP server by deusXmachina-dev that desktop app that captures screen activity, stores AI summaries and OCR text locally, and exposes the history via semantic search and a timeline. It is listed under Knowledge & memory and has 120 GitHub stars.

TypeMcp server
AuthordeusXmachina-dev
RepositorydeusXmachina-dev/memorylane
Popularity120 GitHub stars
CategoryKnowledge & memory
SecurityLow risk (84/100)
Rank#544 of 4,418 MCP servers; #52 in Knowledge & memory
LicenseGPL-3.0
Last commit2026-10-17
RunsLocally and in the cloud
LanguageTypeScript
PlatformsmacOS

Is memorylane safe to install?

memorylane scores 84/100 on the MCPMods security check: Low risk. Things to review: sends your data to a cloud service. It passed 4 of 6 checks.

MCP server results come from listing signals: who publishes it, where your data goes and what it can do. The code itself is not scanned yet.

CheckResult
Community-built serverNote
Sends your data to a cloud serviceReview
No credentials mentionedPass
Read-only by descriptionPass
No code executionPass
Source on GitHubPass

How do I install memorylane?

  1. Find the launch command. The README says how the server starts (npx, uvx, docker or a remote URL) and which API keys it needs.
    https://github.com/deusXmachina-dev/memorylane
  2. Add it to Claude Code. Replace the part after -- with the command from the README. Remote servers use --transport http with a URL.
    claude mcp add memorylane -- <command from README>
    claude mcp add --transport http memorylane <server-url>
  3. Check it connected. This lists your MCP servers and their status.
    claude mcp list

Or ask Claude to set it up

Paste this into Claude Code and it installs memorylane for you:

Add the "memorylane" MCP server from https://github.com/deusXmachina-dev/memorylane to Claude Code. Read its README for the launch command and any API keys I need, run claude mcp add, then check that it connects.