Lucive and AI assistants

Lucive connects to AI assistants in two deliberately different ways:

• Your Journal — through an optional, local-only MCP server that ships inside the desktop app. Entries never leave your machine unless an assistant you enabled reads them into your chat. This page is mostly about that server.
• Your Planning (tasks, intents, scratchpads) — through the Lucive plugin for Claude and ChatGPT, backed by your Lucive account in the cloud. See Planning and the Lucive plugin below.

The split is the point: the Journal is end-to-end encrypted and readable only on your devices, so its assistant access runs on your device. Planning is account-based and agent-readable by design, so its assistant access runs through your account and works from any surface, including your phone.

What MCP actually is

MCP is an open protocol for exposing tools and data to an AI assistant. For the Journal, the assistant runs a small server next to it on your computer. The server speaks a defined set of "tools." The assistant calls those tools when it needs to do something on your behalf.

Lucive's local MCP server exposes journal tools only. It runs as a separate process on your machine and talks to the live Lucive app. Lucive itself doesn't add a relay or a cloud database for this. Once the assistant reads a tool's result, however, that result becomes part of your chat with it and flows to the assistant's provider the same way anything else you type does. More on that at the bottom.

Why it is optional

By default, journal access is off. Lucive runs without it. You only turn it on if you want an assistant to be able to:

• Search your past entries.
• Draft a new entry from a conversation.
• Find the thread that keeps coming back across journals.

When it's off, none of that is possible. By design, and not by accident.

The journal tools

Each tool maps to something you could already do in the app yourself:

The assistant cannot reach the encrypted SQLite file directly. It can only call these tools, and the tools run inside the live Lucive app, with the same permissions you have when you're typing into it.

Want an assistant to put a checklist inside an entry? It just writes one: markdown checkboxes (- [ ] and - [x]) in create_entry or update_entry become real, tappable checkboxes in the entry. They're plain document content, not database records, and they sync with the entry itself.

Task and planning tools used to live here too. They've moved to the Lucive plugin, where they belong: planning is what your account and connected agents are for.

How the server is installed on your machine

The Lucive MCP server ships inside the Lucive app. There is no separate npm package to install. When you enable journal access, Lucive writes a small server bundle (index.js) into its app-support directory and tells your agent where to find it. Concretely, on macOS the bundle ends up at:

~/Library/Application Support/Lucive/mcp-server/index.js

Every install flow below comes down to pointing an agent at that file with Node.

Install for Claude Desktop

Lucive has a one-click installer for Claude Desktop:

1. Open Lucive.
2. Go to Settings → Journal.
3. Turn on "Allow desktop agent applications like Claude to access your journal entries."
4. Click Install for Claude, then restart Claude Desktop.

Under the hood, Lucive writes an entry into Claude Desktop's claude_desktop_config.json that looks roughly like this:

{
  "mcpServers": {
    "Lucive": {
      "command": "node",
      "args": ["/Users/you/Library/Application Support/Lucive/mcp-server/index.js"]
    }
  }
}

That path is specific to your machine, so let Lucive write it for you rather than guessing. If you need to undo the install, Settings → Journal → Disconnect from Claude removes the entry cleanly.

Install for Codex (OpenAI's CLI agent)

Codex doesn't have a one-click installer in Lucive (yet), so you'll add the server through Codex's own MCP servers UI:

1. In Lucive, go to Settings → Journal and enable journal access. (This is also what gets Lucive to write the server bundle to its app-support directory.)
2. In Codex, open Settings → MCP servers → Add server.
3. Fill in the form:
   • Name: Lucive (or whatever you like).
   • Type: STDIO.
   • Command to launch: node.
   • Arguments: add one argument, the absolute path:

     /Users/you/Library/Application Support/Lucive/mcp-server/index.js
     

     (Substitute your home directory.)
   • Environment variables: none needed.
   • Working directory: leave blank or set to your home directory.
4. Save. The next Codex session will see Lucive's journal tools in the tool list.

Verifying it's working

Open Claude Desktop after restart. Start a new chat and ask something like:

What are my journals?

Claude should call list_journals and read back the journals you have in Lucive. If you don't see a tool-call indicator, double-check that Lucive is running and that you restarted Claude Desktop after editing the config.

Turning it off

Two ways:

• In Lucive: Settings → Journal, turn off journal access.
• Or remove the "Lucive" block from the Claude Desktop config and restart Claude.

When journal access is off, your entries are inaccessible to any assistant. Nothing about the rest of Lucive changes.

Planning and the Lucive plugin

Tasks, weekly/monthly/yearly intents, and daily scratchpads connect to assistants through the Lucive plugin, not the local server. The plugin talks to your Lucive account in the cloud, so it works from Claude or ChatGPT on any device, and every connection is separately authorized and revocable in Settings → Planning Account.

You'll need a Lucive account that's signed in on at least one of your devices. Then:

Claude

/plugin marketplace add nickrroberts/lucive-planning
/plugin install lucive@lucive

On first use, the lucive-planning connector asks you to connect: sign in with your email and the 6-digit code Lucive sends you.

ChatGPT / Codex

codex plugin marketplace add nickrroberts/lucive-planning
codex mcp login lucive-planning

Then install Lucive from the app's Plugins screen (Personal tab).

The plugin's tools cover reading your plan for any horizon, adding, updating, completing, and deleting tasks, setting intents, and reading the scratchpad. The Journal is not part of the plugin and cannot be reached through it.

A note on privacy

Lucive's entries are end-to-end encrypted at rest and in sync. When journal access is on, an assistant running on the same machine can ask the live Lucive app for the plaintext of an entry, the same way you can ask Lucive to display it on screen. We don't decrypt anything Lucive isn't already decrypting for you, and the assistant never sees the encrypted SQLite file directly.

Here's the part to be plain about. Once the assistant has read an entry, that text is part of your chat with it. It then travels to that assistant's model provider (Anthropic, OpenAI, whoever else is on the other end) the same way anything else you type to the assistant does. Their terms of service and data-handling policies apply from that point on, not ours. You're extending trust to that provider for the contents of any entry the assistant touches.

That's the tradeoff: more capability in exchange for trusting a third-party model provider with whatever portions of your journal you share with it. It's why journal access is off by default, why we made it easy to disconnect, and why we recommend leaving it off if you'd rather not extend that trust.

Planning data works differently on purpose: it lives in your Lucive account readable by our service, which is exactly what lets connected assistants work with it from anywhere. The full detail is in our privacy policy.

If you have questions or run into trouble, email support@lucive.app.