Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the NSIDC Web Service Documentation Index, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnsidc.org%2Fmain" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnsidc.org%2Fmain" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with NSIDC Web Service Documentation Index API.
Search the NSIDC dataset catalog using OpenSearch query parameters
Retrieve faceted search counts via the /Facets endpoint for filter UIs
Pull the OpenSearch description document for client integration
GET STARTED
For Agents
Search and discover NSIDC snow, ice, and cryosphere datasets through 4 OpenSearch endpoints. Public access with no authentication required.
Use for: Search NSIDC datasets matching 'sea ice extent', Get faceted counts for NSIDC datasets by year, Retrieve the NSIDC OpenSearch description document, List autocomplete suggestions starting with 'glacier'
Not supported: Does not handle dataset downloads, Earthdata authentication, or scientific data processing - use for NSIDC catalog discovery and metadata only.
The NSIDC Web Service Documentation Index lets applications search and discover National Snow and Ice Data Center datasets and metadata via a small set of OpenSearch-style endpoints. Four operations cover faceted search, OpenSearch query and description documents, and a suggest endpoint for autocomplete. It is the integration entry point for tools that need programmatic access to NSIDC's snow, ice, and cryosphere data catalog.
Surface autocomplete suggestions for dataset titles via /suggest
Build cryosphere-data discovery experiences without scraping the NSIDC website
Patterns agents use NSIDC Web Service Documentation Index API for, with concrete tasks.
★ Cryosphere Research Dataset Discovery
Climate researchers and modelers query the NSIDC catalog to find datasets relevant to a study, then export the metadata into provenance trackers. The /OpenSearch endpoint accepts free-text queries and returns dataset titles, IDs, and links, while /Facets supports filter sidebars by year, region, or sensor. This replaces manual catalog browsing on nsidc.org.
Call GET /OpenSearch?q=sea+ice+extent and return the top matching dataset IDs with their NSIDC landing-page URLs
Faceted Filter UIs for Earth Science Portals
Earth-science data portals embed NSIDC search behind faceted UIs. The /Facets endpoint returns counts grouped by year, region, and parameter so the UI can render checkbox filters without the portal team reimplementing search logic. Combined with /suggest for autocomplete, the NSIDC index becomes a drop-in dataset finder.
Call GET /Facets?q=glacier and render the returned facet counts as filter checkboxes in a portal UI
AI Agent Climate Data Lookup via Jentic
Climate-focused AI agents use Jentic to discover NSIDC and answer dataset-recommendation questions. The agent searches Jentic for 'NSIDC dataset search', loads the /OpenSearch schema, and executes a free-text query - returning a ranked list of NSIDC dataset records the user can cite or download.
Use Jentic to search 'NSIDC dataset search', load /OpenSearch, and execute with q=arctic+sea+ice for a research brief
4 endpoints — the nsidc web service documentation index lets applications search and discover national snow and ice data center datasets and metadata via a small set of opensearch-style endpoints.
METHOD
PATH
DESCRIPTION
/OpenSearch
Search NSIDC datasets with OpenSearch query parameters
/OpenSearchDescription
Retrieve the OpenSearch description document
/Facets
Get faceted search counts for filter UIs
/suggest
Autocomplete suggestions for dataset titles
/OpenSearch
Search NSIDC datasets with OpenSearch query parameters
/OpenSearchDescription
Retrieve the OpenSearch description document
/Facets
Get faceted search counts for filter UIs
/suggest
Autocomplete suggestions for dataset titles
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the NSIDC Web Service Documentation Index by hand means constructing OpenSearch queries against nsidc.org and mapping the search, facets, and suggest operations yourself. Through Jentic you install once, import the NSIDC search operations from the API Directory, and your agent calls it, with no credentials to manage because these endpoints are public.
Permission scoping
These search endpoints are read-only and pass terms as query parameters rather than resource ids in the URL path, so scope the agent to the operations it needs, such as running an OpenSearch query or fetching facets. You choose the operations it may call, so the suggest endpoint is not included unless you add it.
Credential isolation
The NSIDC search endpoints are public, so your Jentic One instance routes requests without credentials and there is no key to store or inject. No token ever enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'search NSIDC datasets by keyword', and Jentic returns the GET /OpenSearch operation with its query parameter schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
NSIDC Web Service Documentation Index
Same NSIDC search spec under a longer slug
Choose this only if your tooling indexes the longer slug; endpoints are identical.
Specific to using NSIDC Web Service Documentation Index API through Jentic.
What authentication does the NSIDC Web Service Documentation Index use?
The NSIDC dataset search endpoints are public and require no authentication. Through Jentic, calls are routed without credentials, so the agent can execute /OpenSearch and /Facets queries directly.
Can I search NSIDC datasets by free-text query with this API?
Yes. GET /OpenSearch accepts a query parameter and returns matching NSIDC dataset records as OpenSearch results, including dataset titles, identifiers, and landing-page links.
What are the rate limits for the NSIDC Web Service Documentation Index?
NSIDC does not publish a numeric rate limit for these endpoints, but they are intended for interactive search use. Bulk downloading dataset records should use NSIDC's data distribution channels rather than repeated /OpenSearch calls.
How do I retrieve faceted search counts through Jentic?
Search Jentic for 'NSIDC faceted dataset search', load the GET /Facets schema, and execute with the same query you would pass to /OpenSearch. The flow is pip install jentic, then await client.search, load, and execute.
Is the NSIDC Web Service Documentation Index free?
Yes. NSIDC is a federally funded data center and the search index is open and free. Some downstream dataset downloads may require a free Earthdata login, but not the search endpoints themselves.
Can I limit what my agent is allowed to do with the NSIDC Web Service Documentation Index?
Yes. Because you run Jentic One yourself, your own rules decide which NSIDC operations the agent may call, and these endpoints are read-only search operations that pass terms as query parameters rather than resource IDs in the path. You can scope the agent to just the operations it needs, such as running an OpenSearch query or fetching Facets counts, and leave the suggest endpoint out unless you add it. Since the search endpoints are public, no credentials are involved, so scoping is purely about which read operations the agent is permitted to invoke.