Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Hjarni MCP Server search my notes for decisions I've made about the tech stack"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Hjarni is an AI-native note-taking app. Write notes in Markdown, organize them in folders with custom AI instructions per folder, and let Claude or ChatGPT search, read, create, and organize your notes via MCP.
Your notes serve two readers: you and your AI. Hjarni stores the knowledge. ChatGPT and Claude are the interfaces.
Related MCP server: memex
Hjarni is a hosted remote MCP server with OAuth authentication. No API keys, no Docker, no local setup. Setup takes under 2 minutes.
Open Settings > Integrations
Tap Add custom connector
Set the name to hjarni and the URL to https://hjarni.com/mcp
Tap Add and log in to Hjarni when redirected
Requires Claude Pro or Team plan for MCP integrations.
Add to your MCP config (claude_desktop_config.json or .claude.json):
{
"mcpServers": {
"hjarni": {
"url": "https://hjarni.com/mcp",
"type": "streamable-http"
}
}
}Works on any Claude plan. Authenticates via OAuth on first connection.
Enable Developer mode
Tap Create app
Set the name to hjarni and the MCP Server URL to https://hjarni.com/mcp
Set authentication to OAuth
Tap Create and log in to Hjarni when redirected
Requires ChatGPT Plus, Pro, or Team plan.
Any client that supports streamable HTTP transport can connect. The endpoint is https://hjarni.com/mcp. Authentication uses OAuth 2.0 with PKCE. Discovery metadata is at /.well-known/oauth-authorization-server.
Tool | Description |
| Full-text search across notes, containers, and tags |
| Create a new note with title, body, tags, and container placement |
| Read a single note including full content, tags, and linked notes |
| List notes with filtering by container, tags, and sorting |
| Update content, move notes, change tags, archive/unarchive |
| Permanently delete a note |
| List folders for organizing notes |
| Create new folders |
| Get a single container with its AI instructions |
| Update a container (rename, move, change description) |
| List all tags |
| Create new tags |
| Create or remove bidirectional links between notes |
| Read AI instructions set on a folder |
| Update folder-level AI instructions |
| Attach a file to a note |
| Fetch a file from a URL and attach it to a note |
| Get a temporary download URL for a file |
| Remove a file attachment |
| Overview of the account: note count, containers, tags, inbox |
| List all teams the user is a member of |
| Get team details including recent notes |
The server also exposes MCP prompts for clients that support prompt discovery:
Prompt | Description |
| Summarize a note and suggest tags and related links |
| Review recent activity and suggest organization improvements |
| Synthesize everything in the knowledge base related to a topic |
"What decisions have I made about the tech stack?"
Claude searches your notes, follows wiki-links between related notes, and synthesizes a summary from multiple sources.
"Save this as a note in my Projects folder and tag it"
Claude finds the right container, creates the note with Markdown formatting, adds tags, and links it to related notes.
"Help me triage my inbox"
Claude lists unfiled notes, suggests where each belongs based on your folder structure, and moves them with your approval.
"Draft a project update using my recent meeting notes"
Claude pulls relevant notes and uses them as source material.
Markdown notes with full formatting support
Wiki-links ([[id:Note Title]]) for cross-referencing
Folders with custom AI instructions per folder
Full-text search across all content
Bidirectional linking between notes
Tags for cross-cutting categorization
File attachments (Pro plan and above)
Team collaboration with shared knowledge bases
REST API for custom integrations
Export your data as Markdown at any time
Endpoint |
|
Transport | Streamable HTTP with JSON-RPC 2.0 |
Protocol versions |
|
Authentication | OAuth 2.0 (PKCE) or Bearer token |
Capabilities | Tools and prompts |
For the full protocol reference, see the MCP server docs.
Plan | Price | What you get |
Free | $0 | 25 notes, containers, tags, search, full MCP & API access |
Pro | $10/mo | Unlimited notes, file attachments, share with 2 collaborators |
Teams | $13/seat/mo | Shared knowledge base, team MCP & API, member management |
Also available in EUR and GBP. See pricing.
Email evert@hjarni.com.
This server cannot be deployed
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
Personal context for every AI: search, read, and write back to your private Markdown library.
Securely search, create, and organize your Mem notes and collections from AI assistants.
A self-improving memory layer. Your memory, notes, tasks and goals, remembered everywhere.
