About Opplevagent
Opplevagent MCP Server lets people search Norwegian tours, courses, and activities from MCP clients. Structured filters cover location, category, weather, season, group, age, and price, and results include booking links.
Key features
- 01Search activities with structured filters
- 02Retrieve full details for one experience
- 03List categories and published counts
- 04Read-only access to the public API
Use cases
- 01Finding activities in a Norwegian municipality
- 02Filtering outings by weather, season, or age
- 03Comparing options by group size and price
MCP support
It exposes read-only discovery, experience-detail, and category tools to MCP clients. A remote MCP endpoint is also available over Streamable HTTP.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://opplevagent.no/mcpclaude mcp add --transport http opplevagent https://opplevagent.no/mcp{"mcpServers":{"opplevagent":{"type":"http","url":"https://opplevagent.no/mcp"}}}Open in Cursor{"servers":{"opplevagent":{"type":"http","url":"https://opplevagent.no/mcp"}}}Open in VS Code{"mcpServers":{"opplevagent":{"type":"http","url":"https://opplevagent.no/mcp"}}}{"mcpServers":{"opplevagent":{"serverUrl":"https://opplevagent.no/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
5| Parameter | Type | Required | Description |
|---|---|---|---|
| fylke | string | No | Norwegian county (fylke). Examples: 'Oslo', 'Vestland', 'Troms', 'Rogaland' |
| kommune | string | No | Norwegian municipality (kommune). Examples: 'Tromsø', 'Bergen', 'Stavanger' |
| category | string | No | Experience category slug. Examples: 'natur_friluft', 'dyreliv_safari', 'mat_drikke', 'vinter' |
| weather | enum | No | Weather suitability filter. 'rain'/'snow' prefers indoor + weather-independent experiences. Examples: 'rain', 'clear'rain | snow | clear | any |
| season | string | No | Season filter. Examples: 'summer', 'winter', 'spring', 'autumn' |
| indoor_outdoor | enum | No | Indoor/outdoor preference. Examples: 'indoor', 'outdoor', 'both'indoor | outdoor | both |
| group_size | integer | No | Number of people in the group. Used to filter experiences by min/max group capacity. Example: 4 |
| age | integer | No | Age of the youngest participant. Filters out experiences with a minimum-age requirement above this. Example: 8 |
| max_price | integer | No | Maximum price per person in Norwegian kroner (NOK). Example: 500 |
| duration_max | integer | No | Maximum duration in minutes. Example: 120 (2 hours) |
| language | string | No | Required language for the experience. Examples: 'no', 'en' |
| lat | number | No | Origin latitude for a near-me search (decimal degrees). Must be given together with lng. Example: 69.65 (Tromsø) |
| lng | number | No | Origin longitude for a near-me search (decimal degrees). Must be given together with lat. Example: 18.95 (Tromsø) |
| radius_km | number | No | Max distance from lat/lng in kilometers. Only applies when lat/lng are given. Example: 50 |
| sort | enum | No | 'distance' — sort results ascending by distance from lat/lng. Already the default whenever lat/lng are given; this makes the request explicit.distance |
| limit | number | No | Max results (default 20, max 50) |
Details
From the project READMEOpplevagent MCP Server
MCP server for Opplevagent — discover Norwegian experiences and activities from Claude Desktop, Cursor, or any MCP client.
Search tours, courses and things to do across Norway and filter by county, municipality, category, weather, season, group size, age and price. Every result links straight to a booking page.
Install
Claude Desktop
Add to ~/.claude/claude_desktop_config.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"opplevagent": {
"command": "npx",
"args": ["opplevagent-mcp"]
}
}
}
Restart Claude Desktop. No API key required.
Run directly
npx opplevagent-mcp
Tools
| Tool | Description |
|---|---|
opplev_discover | Search experiences by structured filters: fylke (county), kommune (municipality), category, indoor_outdoor, weather, season, group_size, age, max_price, duration_max, language, limit. Returns ranked experiences with place, category, duration, price and a booking link. |
opplev_info | Get the full profile for one experience by id (UUID) — description, place, season, duration, group size, age suitability, price, languages, accessibility, meeting point and booking link. |
opplev_categories | List all experience categories with the count of published experiences in each. |
All tools are read-only and query the public Opplevagent API. No authentication.
Example prompts
- "Hva kan vi finne på i Oslo når det regner?"
- "Hvalsafari i Tromsø"
- "Familievennlige aktiviteter utendørs i Bergen om sommeren"
- "Things to do in Trondheim under 500 kr"
Categories
kultur_historie · sightseeing_transport · adrenalin_action · dyreliv_safari · vinter_sno · natur_friluft · overnatting_opplevelse · velvaere_spa · mat_drikke
Configuration
| Env var | Default | Purpose |
|---|---|---|
OPPLEVAGENT_URL | https://opplevagent.no | Base URL of the Opplevagent API. Override to point at a staging instance. |
How it works
Opplevagent is an A2A (Agent-to-Agent) marketplace for Norwegian experiences. This MCP server is a thin, read-only wrapper over the public discovery API:
- REST:
https://opplevagent.no/api/opplevelser - Discover:
https://opplevagent.no/api/opplevelser/discover - Agent card:
https://opplevagent.no/.well-known/agent-card.json - OpenAPI:
https://opplevagent.no/openapi.json - Remote MCP (Streamable HTTP):
https://opplevagent.no/mcp
Links
- Website: https://opplevagent.no
- npm: https://www.npmjs.com/package/opplevagent-mcp
- Issues: https://github.com/slookisen/opplevagent-mcp/issues
License
MIT © Daniel Fredriksen
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.