Memlane
@danii1
Memlane is a personal library for links and notes you save from the web. This connector lets agents search your library by meaning, read full saved articles, capture new URLs, create and edit notes, and organize items by project or topic. Sign in once with OAuth; your assistant o
Overview
What is Memlane?
Memlane is an MCP server that connects your Memlane personal library of saved links and notes to AI assistants that support local MCP servers. It lets AI tools search, browse, capture, and organize your Memlane content directly from the chat interface.
How to use Memlane?
Install via npx -y @memlane/mcp or npm install -g @memlane/mcp (then use memlane-mcp). Configure in your MCP host's settings with a JSON block that includes the required MEMLANE_API_KEY environment variable. Restart the host after editing configuration files. For ChatGPT and Claude Desktop, use Memlane's hosted remote MCP endpoint with OAuth instead.
Key features of Memlane
- Semantic search over your saved library
- Browse saves with filters (project, topic, kind, status)
- Fetch full save metadata and body
- Capture a URL (enrichment runs in background)
- Create and update markdown notes
- List and manage projects and topics
Use cases of Memlane
- Search your personal saved links from within an AI assistant
- Capture a new URL while discussing research results
- Browse and filter your library by project or topic
- Create or edit markdown notes tied to specific saves
- Tag or untag saves to keep your library organized
FAQ from Memlane
What does Memlane do that other MCP servers don't?
Memlane provides direct access to your personal Memlane library—saved links, notes, and tags—enabling AI assistants to search, browse, capture, and organize that content without leaving the chat.
What dependencies or runtime does Memlane require?
Node.js 18+ and a Memlane account with an API key (created in the app under Manage → Connections → API keys). The server runs locally via stdio.
Where does my data live?
Data stays in your Memlane account's cloud storage; the MCP server acts as a bridge between the AI assistant and Memlane's API.
What transport and auth options are available?
- Local stdio MCP – uses a
MEMLANE_API_KEYenvironment variable. - Remote MCP endpoint (
https://api.memlane.io/mcp) – uses OAuth sign-in (magic link, no API key). For ChatGPT, Claude Desktop, and other remote MCP clients.
Are there any known limits?
The README does not mention specific rate limits or usage caps. API keys should be kept secret and never committed to version control; leaked keys can be revoked in the Memlane app.
