Set up Hjarni by talking to your LLM

Hjarni publishes a single doc URL that any LLM can read. Paste it into ChatGPT, Claude, Cursor, or Claude Code and your AI knows how to connect the MCP server, propose a folder structure, and seed your first notes. You never leave the chat.

The two URLs you need

Everything else on this page is detail. If you only remember two things, remember these.

Paste in your LLM https://hjarni.com/llms-full.txt

MCP server URL https://hjarni.com/mcp

The first is a plain-text document containing the MCP endpoint, the OAuth metadata, every tool the server exposes, and a step-by-step onboarding script. Any LLM that can fetch a URL can read it and act on it.

Starter prompt

Paste this into ChatGPT, Claude, Cursor, or Claude Code after you have signed up for Hjarni:

“Please read https://hjarni.com/llms-full.txt and help me set up Hjarni. Confirm the MCP connection works, capture a first note about who I am and how I work, then propose a starter folder hierarchy for what I want to capture.”

The AI fetches the doc, walks you through the connection step for your specific client, captures your first note, and then proposes a starter folder hierarchy you can accept or refine before anything else is created.

Per-client install snippets

Sometimes the LLM cannot complete the connection itself (Claude.ai needs you to click through a Connectors menu; Cursor reads a config file). These are the one-line snippets to use for each client.

Claude.ai (web and iOS)

Install Hjarni from the Claude Connectors Directory: one click, Connect, sign in. Or open Customize > Connectors, click Add custom connector, paste the MCP URL, and complete the OAuth flow.

See the full Claude setup guide for per-plan instructions.

Claude Desktop

Same as Claude.ai: install from the Connectors Directory, or open Customize > Connectors, paste the MCP URL, and complete OAuth.

Claude Code

From the command line:

claude mcp add --transport http --scope user hjarni https://hjarni.com/mcp

--scope user makes the server available across every project. Claude Code handles OAuth in your browser.

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "hjarni": {
      "url": "https://hjarni.com/mcp"
    }
  }
}

ChatGPT

Install Hjarni from the ChatGPT Apps Directory: one click, Connect, sign in. If the directory isn't available to you yet, enable Developer mode under Settings > Apps and create an app with the MCP URL; Developer mode is web-only and needs a paid plan, so check it appears on yours.

See the full ChatGPT setup guide for both paths.

Raw curl (smoke test)

If your LLM client cannot do MCP, the core note, folder, and tag tools also have REST endpoints. Generate an API token in your account settings and hit:

curl -H "Authorization: Bearer $HJARNI_TOKEN" https://hjarni.com/api/v1/dashboard

See the REST API reference.

What happens after the connection

Once your LLM can reach the MCP server, the onboarding script in llms-full.txt tells it to:

Read any account-wide AI instructions you have already set, and glance at your dashboard and existing folders so it reuses what is already there.
Ask a few quick questions about who you are and how you work, then save the answers as your first note. That note is the one required step, and it comes before any folders.
Offer to save the working preferences from that conversation as account-wide AI instructions.
Only then: ask which persona fits best (developer, founder, researcher, writer, or traveler), propose a starter folder hierarchy, and wait for your approval before creating anything, with folder-level AI instructions so future sessions follow the same conventions.

From that point your LLM is reading and writing notes through the same MCP server every time you start a new conversation.

Troubleshooting

The LLM says it cannot fetch the URL

Some chat clients block outbound HTTP unless you explicitly enable a "web" or "browse" tool. Turn that on, or paste the contents of llms-full.txt directly into the chat.

The LLM connected MCP but tool calls return 401

The OAuth flow probably did not complete. Disconnect the server in your client's connectors menu and add it again. The browser handoff should land on a Hjarni consent screen.

The LLM creates folders without asking

Repeat the starter prompt and add: "Show me your plan before creating anything." The doc instructs the LLM to confirm before mutating, but some clients are more eager than others.

The LLM keeps offering tools that look wrong

It is probably using a cached older copy of the doc. Ask it to refetch https://hjarni.com/llms-full.txt. The file is auto-generated from the live tool definitions, so it is always current.

Give your AI a memory. Free.

Connect Claude or ChatGPT to notes they can actually read and write.

Get started free