Provides tools for querying flood and landslide risk data from NVE's ArcGIS REST services, including flood risk zones, landslide hazard areas, and quick clay risk zones.
Click on "Install 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., "@nor-data/nve-mcp Check flood risk at 59.913, 10.752"
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.
MCP-server som wrapper NVE sine åpne kartdata (kart.nve.no/enterprise ArcGIS REST) for punktoppslag på naturfare. Bygget for Konsept 12 («Hva gjør naboene?») — feltene flood_risk og landslide_risk i 12-feltmatrisen.
hent_flomaktsomhet(lat, lon)Flom-aktsomhetsområde (landsdekkende GIS-analyse, Flomaktsomhet/1)
Dekningssjekk (Flomaktsomhet/2) — skiller «ingen treff» fra «ikke analysert»
Detaljert 200-årsflomsone (Flomsoner2/17) + analysert-område-sjekk (Flomsoner2/0) der detaljert flomsonekart finnes (TEK17 §7-2-referanse)
hent_skredaktsomhet(lat, lon)Snø-/steinskred aktsomhet (SkredSnoSteinAkt/0) + kartlagt-sjekk (lag 1)
Jord-/flomskred aktsomhet (JordFlomskredAktsomhet/1 — lag 0 er raster, ikke spørrbart)
Kvikkleire faregradssoner (SkredKvikkleire2/0) + kartlagt-sjekk (lag 2)
Skredtype-koder dekodes (begge NVE/NGU-domener: korte koder 1–99 og fulle koder 110–200)
Related MCP server: @nor-data/nabolag-mcp
Brukeren er tolkeren: output forklarer eksplisitt at aktsomhet ≠ faresone
Synlig usikkerhet: dekningslag rapporteres alltid — «ingen treff» utenfor kartlagt område betyr «ikke kartlagt», ikke «trygt»
Kildelenke per datapunkt: hver respons inkluderer tjeneste-URL + temakart-innsyn + lisens
Testpunkt | Forventet | Resultat |
Lillestrøm (59.956, 11.046) | flom-treff | ✅ FlomAktsomhetOmr + utenfor 200-årssone (detaljkart finnes) |
Thorvald Meyers gate 2C, Oslo | rent | ✅ ingen treff, innenfor analysert område |
Ytterholtet 1, Sørreisa | snø/stein-treff | ✅ PotensieltSkredfareOmr («Snø og steinskred») |
Gjerdrum (60.063, 11.036) | kvikkleire-treff | ✅ UtlosningOmr |
npm install && npm run build
node dist/index.js # stdio MCP
node test-e2e.mjs # ende-til-ende-testRegistrert i ~/.claude.json som nve. Lisens: MIT. Data: NVE/NGU åpne data (NLOD/CC BY).
Sjekk om et koordinat (WGS84) ligger i NVE sitt flom-aktsomhetsområde (landsdekkende GIS-analyse) og i detaljert kartlagt flomsone (200-årsflom) der slik finnes. Returnerer også om punktet er innenfor analysert/kartlagt område, slik at 'ingen treff' kan skilles fra 'ikke kartlagt'. Kilde: NVE (kart.nve.no), åpne data.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | Breddegrad (WGS84, f.eks. 59.93 for Oslo) | |
| lon | Yes | Lengdegrad (WGS84, f.eks. 10.76 for Oslo) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that the tool distinguishes between 'no hit' and 'not mapped' and mentions the source and geographic scope. It does not clarify read-only nature but implies safety through lookup operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the main action, and efficient. Every sentence adds value: what it checks, what it returns, and the source.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description explains the key return distinction (no hit vs. not mapped). It does not specify exact format but is adequate for a lookup tool with two numeric parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description does not add parameter-level details beyond what schema provides (WGS84, examples). It reinforces the coordinate system but adds minimal semantic value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks if a coordinate lies within NVE's flood risk area and detailed flood zone. It distinguishes from the sibling tool 'hent_skredaktsomhet' (landslide) by specifying flood-related functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context (checking flood risk for coordinates) but does not explicitly state when to use this tool vs. the sibling tool. However, the purpose is distinct enough that an agent can infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sjekk om et koordinat (WGS84) ligger i NVE sine skred-aktsomhetsområder: snø-/steinskred, jord-/flomskred og kvikkleire (faregradssoner). Returnerer treff per skredtype med dekodet skredtype og kartleggingsstatus, slik at 'ingen treff' kan skilles fra 'ikke kartlagt'. Kilde: NVE/NGU (kart.nve.no), åpne data.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | Breddegrad (WGS84, f.eks. 59.93 for Oslo) | |
| lon | Yes | Lengdegrad (WGS84, f.eks. 10.76 for Oslo) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It explains the return value structure (hits per type, decoded type, mapping status) and distinguishes 'no hits' from 'not mapped'. However, it lacks details on error handling, rate limits, or authentication. Given the simplicity, the transparency is adequate but not exceptional.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences that cover purpose, return value, and data source. No redundant or irrelevant information. Front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (2 required parameters, no output schema), the description adequately covers input, output semantics, and data provenance. It could mention potential errors for out-of-range coordinates, but the schema constraints partially address that. Overall complete for its purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% as both parameters (lat, lon) have descriptions in the schema. The tool description does not add further meaning beyond the schema's parameter descriptions, so it meets the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'sjekk' (check) and the resource 'skred-aktsomhetsområder' (avalanche hazard areas). It specifies the coordinate system (WGS84) and lists covered hazard types. The sibling tool 'hent_flomaktsomhet' is for flood hazard, providing clear differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use it (to check if a coordinate lies in avalanche hazard areas). It does not explicitly state when not to use it or provide alternatives beyond the sibling, but the context of hazard types and coordinate checking is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools address entirely different hazard types (flood vs landslide), with no overlap in their functionality. Clear distinction.
Both tools follow the same 'hent_' + hazard type pattern, using snake_case and Norwegian, providing a predictable naming convention.
With only 2 tools, the server is very narrow in scope. However, this may be appropriate for a focused hazard query service, though it feels slightly thin.
The server covers the two main hazard queries (flood and landslide) but lacks other potential hazard types (e.g., storm surge, wildfire) and has no data manipulation tools. Adequate for its stated purpose but not comprehensive.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Mireye Earth — federal-source-cited geospatial data for any MCP-aware agent.
Flood MCP — wraps Open-Meteo Flood API (free, no auth)
Geospatial MCP server for earthquake, tsunami, volcano, disaster, and FX data queries.
Canonical British Columbia Property Intelligence & Risk Screening MCP Server.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/3121n/nor-data-nve-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
