Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the NOAA ERDDAP API, 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%2Fnoaa.gov%2Fcoastwatch" | 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%2Fnoaa.gov%2Fcoastwatch" | 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 NOAA ERDDAP API.
Run a full-text search across NOAA's ERDDAP dataset collection
Run an advanced search filtered by dataset attributes
List dataset metadata and variables for a given dataset id
Query tabular datasets and return the selected rows as JSON or CSV
Query gridded datasets and return a subset as JSON
GET STARTED
Browse datasets by category attribute and value
Convert between ISO time strings and ERDDAP numeric time values
Patterns agents use NOAA ERDDAP API for, with concrete tasks.
★ AI Environmental Data Agent
An AI agent connected through Jentic answers questions about ocean and atmospheric conditions by searching ERDDAP for a matching dataset, reading its metadata, and querying the values, so a user asking for recent buoy temperatures gets real numbers without the developer learning ERDDAP's query grammar. The agent finds the dataset id first, then pulls the rows it needs as JSON.
Search ERDDAP for a sea surface temperature dataset, read its variables, and query the most recent rows for a bounding box as JSON
Research Data Extraction
A research or data-science pipeline pulls environmental time series by resolving a dataset id, then requesting a tabular query filtered to the variables, station, and time range it needs. CSV output drops straight into analysis tools, and advanced search narrows the catalogue to the datasets that carry the required variables.
Query a tabular dataset for a single station over a date range and return the result as CSV
Gridded Data for Mapping
A mapping or modelling tool pulls a spatial subset of a gridded dataset such as chlorophyll or sea surface temperature by requesting a griddap query bounded to a latitude, longitude, and time window. The JSON response feeds a heatmap or model input without the tool downloading the entire grid.
Request a griddap subset of a sea surface temperature grid for a latitude and longitude box and return it as JSON
10 endpoints — the noaa erddap api provides restful access to oceanographic, atmospheric, and environmental datasets served by noaa coastwatch.
METHOD
PATH
DESCRIPTION
/search/index.json
Full-text search for datasets
/info/{datasetId}/index.json
Get metadata for a specific dataset
/tabledap/{datasetId}.json
Query a tabular dataset and return JSON
/tabledap/{datasetId}.csv
Query a tabular dataset and return CSV
/griddap/{datasetId}.json
Query a gridded dataset and return JSON
/categorize/index.json
List dataset categorization attributes
/convert/time.json
Convert between time string and numeric formats
/search/index.json
Full-text search for datasets
/info/{datasetId}/index.json
Get metadata for a specific dataset
/tabledap/{datasetId}.json
Query a tabular dataset and return JSON
/tabledap/{datasetId}.csv
Query a tabular dataset and return CSV
/griddap/{datasetId}.json
Query a gridded dataset and return JSON
/categorize/index.json
List dataset categorization attributes
/convert/time.json
Convert between time string and numeric formats
What agents get from Jentic-routed access to this vendor.
Setup
NOAA ERDDAP needs no API key, but wiring it by hand means learning its tabledap and griddap query grammar, dataset ids, and JSON or CSV output modes. Through Jentic you install once, import it from the API Directory, and your agent calls it.
Permission scoping
Every operation is a read, so a rule can keep your agent to just the search and dataset-query operations. You choose which operations it may call, and there is no write path to NOAA's data.
Credential isolation
ERDDAP is public, so there is no key to manage. When you add APIs that do require credentials, your own Jentic One instance keeps them encrypted and injects them at execution time, never placing them in the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find a sea temperature dataset' or 'query a tabular dataset', and Jentic returns the matching ERDDAP operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using NOAA ERDDAP API through Jentic.
What authentication does the NOAA ERDDAP API use?
The NOAA ERDDAP API is public: its OpenAPI spec declares no authentication, so search and dataset-query requests need no API key. Through Jentic it is still called from your own self-hosted instance, with every call logged.
Can I query tabular datasets with the NOAA ERDDAP API?
Yes. The tabledap operations take a dataset id and return the selected rows and variables as JSON or CSV, while griddap does the same for gridded data as JSON. You locate the dataset id first through full-text or advanced search.
What are the rate limits for the NOAA ERDDAP API?
The OpenAPI spec does not define rate limits for the NOAA ERDDAP API. NOAA asks users to query responsibly and documents guidance at https://coastwatch.pfeg.noaa.gov/erddap, so check there before scheduling heavy pulls.
Can I limit what my agent is allowed to do with the NOAA ERDDAP API?
Yes. Write a rule that allows only the search and dataset-query operations, so the agent reads environmental data and nothing else. ERDDAP exposes no write operations, so there is nothing to change, and every call the agent makes is logged.
How do I query a NOAA dataset through Jentic?
Search by intent in Jentic with a query like 'query an ERDDAP dataset', add the NOAA ERDDAP API from the Jentic API Directory, and your agent runs the search to find a dataset id then the tabledap or griddap query to pull the data. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Search NOAA's ERDDAP dataset collection, inspect dataset metadata, and query tabular or gridded environmental data as JSON or CSV. Public access with no API key.
Use for: Search NOAA ERDDAP for sea surface temperature datasets, Get the metadata and variables for a specific dataset, Query a tabular dataset and return CSV, Retrieve a subset of a gridded dataset as JSON
Not supported: Does not handle data visualization, forecasting, or dataset hosting. Use for searching and querying NOAA ERDDAP environmental datasets only.
The NOAA ERDDAP API provides RESTful access to oceanographic, atmospheric, and environmental datasets served by NOAA CoastWatch. It runs full-text and advanced dataset searches, lists dataset metadata and variables, and queries tabular (tabledap) and gridded (griddap) data with JSON or CSV output. A time-conversion endpoint and category browsing round out a service built for pulling environmental data into analysis pipelines.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>