mcpField
M
Memlane

Memlane

Local
github.com/danii1Developer Tools0Updated 19w ago
Repository

About Memlane

Memlane connects a personal library of saved links and notes to AI assistants, with semantic search and tools to read and organize saved content. It supports a local API-key setup and a hosted endpoint using OAuth.

Key features

  1. 01Semantic search across saved items
  2. 02Browse and filter library entries
  3. 03Read full saved articles
  4. 04Capture URLs and edit notes
  5. 05Organize items by project and topic

Use cases

  1. 01Find saved material by meaning
  2. 02Read the full text of saved articles
  3. 03Save a URL or edit a note
  4. 04Add or remove topics on saved items

MCP support

Exposes tools for searching, browsing, reading, capturing, and organizing Memlane library items to MCP clients. The local server uses an API key; remote clients can connect through an OAuth endpoint.

#memory#second-brain#bookmarks#notes#links

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "memlane": {
      "command": "npx",
      "args": [
        "-y",
        "@memlane/mcp"
      ],
      "env": {
        "MEMLANE_API_KEY": "<MEMLANE_API_KEY>"
      }
    }
  }
}
Run commandnpx -y @memlane/mcp
Environment variables to set
MEMLANE_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@memlane/mcp

Tools

10

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
querystringYesNatural-language search query
limitintegerNo

Details

From the project README

@memlane/mcp

Connect Memlane, your personal library of saved links and notes, to AI assistants that support local MCP servers.

Prerequisites

  1. A Memlane account
  2. An API key from Manage → Connections → API keys in the app
  3. Node.js 18+ (for npx)

Configuration

This server runs locally via stdio. Most compatible hosts use the same JSON shape:

{
  "mcpServers": {
    "memlane": {
      "command": "npx",
      "args": ["-y", "@memlane/mcp"],
      "env": {
        "MEMLANE_API_KEY": "ml_live_…"
      }
    }
  }
}
VariableRequiredDefault
MEMLANE_API_KEYYesn/a
MEMLANE_API_URLNohttps://api.memlane.io

After npm install -g @memlane/mcp, you can use "command": "memlane-mcp" instead of npx.

Supported hosts

HostWhere to add the config
CursorSettings → MCP, or .cursor/mcp.json in a project
Claude Codeclaude mcp add memlane -- npx -y @memlane/mcp (pass -e MEMLANE_API_KEY=…)
Windsurf~/.codeium/windsurf/mcp_config.json
VS Code + Copilot.vscode/mcp.json — see below
Gemini CLI~/.gemini/settings.json

For ChatGPT and Claude Desktop, use the remote MCP endpoint instead (OAuth, no API key).

Restart the host app after editing config files.

VS Code

VS Code uses "servers" as the root key (not "mcpServers"):

{
  "servers": {
    "memlane": {
      "command": "npx",
      "args": ["-y", "@memlane/mcp"],
      "env": {
        "MEMLANE_API_KEY": "ml_live_…"
      }
    }
  }
}

Enable MCP in VS Code settings: "chat.mcp.enabled": true.

ChatGPT and remote MCP hosts

ChatGPT, Claude Desktop, Claude on the web, and other remote MCP clients cannot run npx. Use Memlane's hosted endpoint instead:

URL: https://api.memlane.io/mcp

  1. In your AI app, add a custom MCP connector with that URL.
  2. Complete the OAuth sign-in flow (Memlane account: magic link or future social providers).
  3. Approve access on the consent screen.

No API key required. Disconnect by removing the connector in your AI app's settings.

Tools

The local server exposes 10 MCP tools. Full function reference:

  • docs/TOOLS.md — what each tool does, parameters, return shapes, and workflow tips
  • docs/API.md — REST mappings, auth scopes, and curl examples
ToolDescription
search_savesSemantic search over your library
list_savesBrowse saves with filters (project, topic, kind, status)
get_saveFetch metadata; optional full markdown body
capture_urlSave a URL (enrichment runs in the background)
create_note / update_noteCreate or edit markdown notes
list_projects / list_topicsList projects and topics
add_topic_to_save / remove_topic_from_saveTag or untag a save

Security

API keys are secrets. Store them in your MCP host's environment config. Never commit them to version control. Revoke a leaked key in Manage → Connections → API keys.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.