# One knowledge base. Every AI tool.

Hjarni is an [MCP knowledge base](https://hjarni.com/mcp-knowledge-base) with a built-in server. Pick the AI tool you already use. The config snippet on each page is two minutes of setup.

[Hjarni for Claude](https://hjarni.com/for/claude)

Long-term memory for Claude.ai, Claude Desktop, and Claude iOS.

[Hjarni for ChatGPT](https://hjarni.com/for/chatgpt)

Connect Hjarni in the ChatGPT Apps Directory or developer mode.

[Hjarni for Cursor](https://hjarni.com/for/cursor)

Give your AI editor the architecture context that is not in the repo.

[Hjarni for Claude Code](https://hjarni.com/for/claude-code)

One CLI command. OAuth in the browser. Hjarni in every session.

[Hjarni for Windsurf](https://hjarni.com/for/windsurf)

Windsurf MCP server. Cascade reads, writes, and searches your knowledge base.

[Hjarni for Cline](https://hjarni.com/for/cline)

Cline MCP server. Long-term memory in the VS Code panel.

[Hjarni for GitHub Copilot](https://hjarni.com/for/copilot)

GitHub Copilot MCP server. Agent mode reads your knowledge base in VS Code.

[Hjarni for Zed](https://hjarni.com/for/zed)

Zed MCP server. Long-term memory in the assistant panel.

[Hjarni for Continue.dev](https://hjarni.com/for/continue-dev)

Continue.dev MCP server. Long-term memory in VS Code and JetBrains.

[Hjarni for Aider](https://hjarni.com/for/aider)

MCP server for Aider, the open-source CLI pair programmer.

[Hjarni for Goose](https://hjarni.com/for/goose)

MCP extension for Goose, the open-source AI agent originally built at Block.

[Hjarni for Open WebUI](https://hjarni.com/for/openwebui)

Native MCP for Open WebUI's External Tools panel, with mcpo as a fallback.

[Hjarni for Raycast](https://hjarni.com/for/raycast)

Raycast AI MCP server. Search and capture from the Mac launcher.

[Hjarni for Alfred](https://hjarni.com/for/alfred)

Alfred workflow that captures into Hjarni via the REST API.

[Hjarni for Obsidian](https://hjarni.com/for/obsidian)

Sync Hjarni notes into an Obsidian vault as plain Markdown.

[Hjarni for Gemini CLI](https://hjarni.com/for/gemini-cli)

MCP server for Gemini CLI, Google's terminal agent. Runbooks one command away.

[Hjarni for Perplexity](https://hjarni.com/for/perplexity)

Custom MCP connector for Perplexity. Answers from your notes, not just the web.

[Hjarni for Junie](https://hjarni.com/for/junie)

MCP server for Junie, JetBrains' AI coding agent. Conventions it reads while it codes.

[Hjarni for LibreChat](https://hjarni.com/for/librechat)

LibreChat MCP server. One memory across every model provider in your self-hosted hub.

[Hjarni for Jan](https://hjarni.com/for/jan)

MCP server for Jan, the private, local-first AI app. Memory for your offline model.

[Hjarni for LM Studio](https://hjarni.com/for/lm-studio)

LM Studio MCP server. Long-term memory for the local models you run.

[Hjarni for n8n](https://hjarni.com/for/n8n)

MCP Client Tool node for n8n. Agents that read and write your notes mid-workflow.

## Pick any tool. Switch later. Bring your notes.

Every page above points at the same Hjarni MCP server. The same notes, folders, and tags show up in Claude today and Cursor tomorrow. There is no per-tool data to migrate.

Using a remote MCP client that is not listed? The endpoint is `https://hjarni.com/mcp` with OAuth. Config shapes vary by client (some want `url`, some want `serverUrl`, some use a CLI). The [MCP Config Validator](https://hjarni.com/mcp-config-validator) can sanity-check a config before you save it.

> Hjarni ran the whole [Labeur](https://apps.apple.com/app/id6761388629) launch. Scope decisions, landing page copy, App Store submission, launch day checklist, all in one place and all in sync with Claude. I stopped re-explaining myself to the AI. From first sketch to live in the store.

[Joren De Groof, Not A Tech Company](https://notatechcompany.be/)