opplevagent-mcp

MCP serverAI & models

This gives your AI access to a Norwegian experiences marketplace, so it can help you find things to do across Norway. Once added, your AI can search for activities and experiences and narrow them down by location, type, season, weather, and how many people are going.

Available today. Use it from your connected AI after setup.

After adding it, ask your AI what you can do in a specific county or season. For example, try something like indoor activities for a group of eight on a rainy day.

Then ask your AI: use the discover experiences tool from opplevagent-mcp

What your AI can do with it

  • Find experiences across Norwegian counties
  • Browse activities by category
  • Filter activities by weather conditions
  • Search for experiences by season
  • Match activities to your group size

Install opplevagent-mcp

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user opplevagent-mcp 'https://opplevagent.no/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://opplevagent.no/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=opplevagent-mcp&config=eyJ1cmwiOiJodHRwczovL29wcGxldmFnZW50Lm5vL21jcCJ9

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://opplevagent.no/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add opplevagent-mcp --url 'https://opplevagent.no/mcp'

    Run it once, then sign in with codex mcp login opplevagent-mcp if the server asks for an account.

From the project's README

As published by slookisen/lokal in README.md. This repository publishes several servers, so only the opening is shown here.

Live: https://rettfrabonden.com | MCP Server: https://rettfrabonden.com/mcp | API Spec: https://rettfrabonden.com/openapi.yaml

Rett fra Bonden is the discovery layer for local food in Norway. 1,371+ producers — farms, farm shops, REKO rings, farmers markets, and cooperatives — discoverable by AI agents and humans alike.

Not an app. Not a webshop. Infrastructure — the DNS for food agents.

Use Rett fra Bonden

From Claude (remote MCP via Claude Connectors)

The recommended setup for Claude.ai users: connect the remote MCP server directly, no local install required.

  • MCP Server URL: https://rettfrabonden.com/mcp
  • Transport: Streamable HTTP (MCP protocol 2025-06-18)
  • Authentication: None required — the server is publicly accessible

Once connected, ask Claude things like:

  • "Finn økologiske grønnsaker nær Oslo som leverer hjem"
  • "Which dairy farms in Rogaland sell raw milk directly to consumers?"
  • "Compare three honey producers in Innlandet — who ships nationwide?"

From Claude Desktop (MCP stdio)

If you prefer a local install over remote:

Shortened here. Read the whole README on GitHub.

Tools it offers (5)

What this server listed when ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • discover_experiences
  • list_experience_categories
  • get_experience
  • discover_gardssalg
  • book_gardssalg

Signals

GitHub stars
2
Last commit
Sep 2026
Weekly downloads
34
Advanced
Delivery
opplevagent-mcp MCP server → your ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-slookisen-opplevagent-mcp
Source
github.com/slookisen/lokal
Hosted endpoint
https://opplevagent.no/mcp