You're In. Let's Wire Up Your Engine.
Connect Claude, ChatGPT, Cursor, or VS Code by signing in with Haakon, or use a platform key. Either takes under a minute.
Sign In with Haakon
Add the Haakon server URL to your tool, then sign in with this same account and approve the connection. No key to copy or paste, and you can disconnect any time from the tool's connector settings.
Every connection uses the same URL, which has no key in it:
https://api.haakon.ai/mcp/haakon
Requires an active Haakon plan (the Free plan counts). If you see "An active Haakon plan is required", choose a plan on this page and you'll be sent back to finish connecting.
Claude (claude.ai, Claude Desktop)
- Settings → Connectors → Add custom connector.
- Name it
Haakonand paste the URL above. - Click Connect, sign in to Haakon if asked, then click Approve.
Claude Code
Run this in your terminal, then type /mcp, select haakon, and choose Authenticate:
claude mcp add haakon --transport http https://api.haakon.ai/mcp/haakon
ChatGPT (also Codex)
In the app: Plugins → MCPs → Add server, paste the URL, and choose OAuth if asked how to authenticate. In a browser, turn on Developer Mode first (Settings → Security and login), then add the URL as a custom connector. Codex CLI:
codex mcp add haakon --url https://api.haakon.ai/mcp/haakon
Then type /mcp in Codex CLI and select haakon to sign in.
Cursor
Add this to .cursor/mcp.json, then open Cursor Settings → Tools & MCPs and click Connect next to haakon:
{
"mcpServers": {
"haakon": {
"url": "https://api.haakon.ai/mcp/haakon"
}
}
}
VS Code
Add this to .vscode/mcp.json (the root key is servers), then start the server when prompted and sign in:
{
"servers": {
"haakon": {
"type": "http",
"url": "https://api.haakon.ai/mcp/haakon"
}
}
}
Gemini and any tool without a sign-in prompt: use Option 2 below.
Connect with a Platform Key
For tools without a sign-in prompt (such as Gemini), or if you prefer a key. Step 1: generate a key. Step 2: paste it into the connection URL below. Treat the key like a password, since anyone with it can use your plan.
Add the Key URL to Your Tool
Replace YOUR_HAAKON_KEY with the key you generated above. It goes directly in the connection URL below, with no separate provider key required.
Claude (claude.ai, Claude Desktop, Claude Code)
Settings → Connectors → Add custom connector, then paste this URL:
https://api.haakon.ai/mcp/haakon?key=YOUR_HAAKON_KEY
ChatGPT (also works in Codex — same connector list)
In the app: Plugins → MCPs → Add server, then paste this URL. No separate token or headers needed — your key travels in the URL itself.
https://api.haakon.ai/mcp/haakon?key=YOUR_HAAKON_KEY
Using ChatGPT in a browser instead of the app? Custom connectors there require a Plus, Pro, Business, or Enterprise plan with Developer Mode enabled first (Settings → Connectors → Advanced, or Settings → Security and login) before you'll see the same Add connector option.
Gemini
Custom MCP connectors are currently part of Gemini Spark (personal Google accounts, 18+, US only, as this feature continues rolling out). Go to Settings & help → Connected Apps, and enter the URL below — no separate credentials needed, since your key travels in the URL itself:
https://api.haakon.ai/mcp/haakon?key=YOUR_HAAKON_KEY
Other IDEs & Agent Frameworks (Cursor, VS Code, etc.)
These connect straight to the same remote server — no local install needed.
Cursor — .cursor/mcp.json
{
"mcpServers": {
"haakon": {
"url": "https://api.haakon.ai/mcp/haakon?key=YOUR_HAAKON_KEY"
}
}
}
VS Code — .vscode/mcp.json (note the root key is servers, not mcpServers)
{
"servers": {
"haakon": {
"type": "http",
"url": "https://api.haakon.ai/mcp/haakon?key=YOUR_HAAKON_KEY"
}
}
}
Available Tools: haakon, haakon_help
Setup
Haakon doesn't choose or change which model your AI tool uses -- that's set wherever you're calling from (Claude, ChatGPT, Gemini, Cursor, VS Code). Haakon's cognitive lenses extend whatever model is already selected there; they don't substitute for one.
- For low-cost, fast performance: keep a flash or fast model selected in your calling tool. A lens applied to a fast model is what gets you closer to frontier-level output at flash-model cost.
- For maximum quality regardless of cost: select a premium or frontier model in your calling tool. Haakon's lenses extend that model's reasoning further still.
Cognitive Lenses
Pass these configuration flags into your IDE requests or MCP tool payloads to forcefully alter the LLM's reasoning framework.