Nps Gov National Park Service API
Official vendor OpenAPI document · agent-readyMaps GeolocationPlaces SearchapiKey29 EndpointsREST
For Agents
List national parks, campgrounds, alerts, events, and visitor centers, and read park boundary map data with the National Park Service API. Covers 29 read-only endpoints across parks and related content.
Use for: List the national parks in a given state, Find campgrounds within a specific park, Check the current alerts for a park, List upcoming events at a park
Not supported: Does not handle reservations, ticketing, or payments. Use for reading park information, alerts, and related content only.
The National Park Service API provides data about US national parks, exposing parks, campgrounds, alerts, events, places, and visitor centers over a REST interface. It lets you list parks and filter them by state, read current alerts and closures, find campgrounds and things to do, and retrieve park boundary map data. Requests carry an API key as a query parameter and return structured JSON your application can act on.
Install Jentic One Beta
Connect the National Park Service API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the National Park Service 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.
1
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%2Fnps.gov%2Fnps" | sh2
Step 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%2Fnps.gov%2Fnps" | 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.
Capabilities
What an agent can do with National Park Service API.
List national parks and filter them by state or query
List campgrounds and read their details
Read current park alerts and closures
List events and things to do at parks
List places and visitor centers
Retrieve park boundary map data for a park by its site code
Use Cases
Patterns agents use National Park Service API for, with concrete tasks.
★ AI Travel Planner via Jentic
An AI travel planner can build a national park itinerary without a developer wiring the NPS API by hand. Through Jentic the agent searches for the parks and things-to-do operations by intent, receives the endpoints and their input schemas, and calls them with the API key injected at execution time. The planner then assembles parks, campgrounds, and activities into a trip.
Search Jentic for 'list parks by state', call GET /parks for the state, then GET /thingstodo and GET /campgrounds for the chosen parks
Park Alert Monitoring
Applications that inform visitors need current closures and warnings for the parks they cover. The National Park Service API reads active alerts, so a monitoring job can surface closures before a visitor sets out. Because the alerts come straight from NPS, the notices stay current with official park status.
Call GET /alerts filtered to the target parks and surface any active closures or warnings
Park Content Directory
Travel sites that list national parks need structured details for each one. The NPS API reads parks, visitor centers, and places, so a build job can assemble a directory of parks with their facilities. This keeps the directory aligned with the official park data.
Call GET /parks for the base list, then GET /visitorcenters and GET /places to enrich each park entry
Key Endpoints
29 endpoints — the national park service api provides data about us national parks, exposing parks, campgrounds, alerts, events, places, and visitor centers over a rest interface.
METHOD
PATH
DESCRIPTION
GET
/parks
List parks
GET
/campgrounds
List campgrounds
GET
/alerts
List park alerts
GET
/events
List events
GET
/places
List places
GET
/visitorcenters
List visitor centers
GET
/thingstodo
List things to do
GET
/mapdata/parkboundaries/{sitecode}
Get park boundary data
GET
/parks
List parks
GET
/campgrounds
List campgrounds
GET
/alerts
List park alerts
GET
/events
List events
GET
/places
List places
GET
/visitorcenters
List visitor centers
GET
/thingstodo
List things to do
GET
/mapdata/parkboundaries/{sitecode}
Get park boundary data
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the National Park Service API by hand means appending your API key to every query string and calling each park, alert, and campground endpoint yourself. Through Jentic you install once, import the API from the API Directory, store the key once, and your agent calls it.
Permission scoping
The National Park Service API is read-only; every operation is a GET. A rule can still narrow the agent to just the resources it needs, such as GET /parks and GET /alerts, while withholding others. You choose which operations the agent may call.
Credential isolation
Your National Park Service API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'list parks by state' or 'read park alerts', and Jentic returns the matching National Park Service operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using National Park Service API through Jentic.
What authentication does the National Park Service API use?
The National Park Service API authenticates with an API key passed as a query parameter, as declared in its OpenAPI spec. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt, logs, or context.
Can I list parks by state with the National Park Service API?
Yes. Call GET /parks and filter by state to return the parks in that state, then call GET /campgrounds or GET /thingstodo to enrich each park. All responses are JSON your agent can parse directly.
What are the rate limits for the National Park Service API?
The OpenAPI spec does not specify rate limits. Check the National Park Service developer documentation at https://www.nps.gov/subjects/developer/ for current limits before running high-volume requests.
How do I read park alerts through Jentic?
Search Jentic for 'list park alerts', which resolves to the GET /alerts operation, and Jentic returns its input schema so your agent can filter alerts to the parks it covers. Credentials are injected at call time from your own instance. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I restrict what my agent is allowed to do with the National Park Service API?
Yes. The API is read-only, and you can still narrow the agent to just the resources it needs, such as GET /parks and GET /alerts, while withholding the rest, and every call it makes is logged by your own instance. You add other operations to the allowed set only when you decide to.
Is there a National Park Service MCP server?
You don't need an MCP server to give your agent the National Park Service API. Jentic connects it directly from the API Directory: import the API, store your key once, and your agent calls the parks, alerts, and campground operations on demand without loading another server's tool definitions into its context.
GET STARTED