national-parks-mcp-server

national-parks-mcp-server: find parks

nps_find_parks

Read-only

Resolve a place name, US state, or free-text query to National Park Service parks — the required first step before the detail tools. Returns each park's parkCode (the key nps_get_park, nps_get_alerts, nps_find_campgrounds, nps_get_activities, and nps_find_events all use) plus a compact trip-planning summary (designation, states, description, coordinates, headline activities, entrance fee, NPS page). Coverage is US NPS sites only — national parks, monuments, historic sites, seashores — not state parks and not Forest Service or BLM land.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum parks to return (1–50). The full set is ~470 sites; narrow with query/stateCode rather than paging through everything.
`query`	No	Free-text search across park names and descriptions (e.g. "yosemite", "civil war", "redwood"). Exact parkCode or name matches lead, then other name matches, then parks that only mention the term in their description — ranked across every match before start/limit apply. Omit to browse by state. At least one of query or stateCode is recommended; with neither, returns the first page of all ~470 NPS sites.
`start`	No	Zero-based offset for pagination within the matched set. Use with limit to page through results.
`activity`	No	Filter to parks offering an activity, matched against each park's activities list (e.g. "hiking", "camping", "stargazing"). Case-insensitive substring match, combined with query/stateCode and applied before start/limit, so totalCount counts every matching park, not one page. Use nps_get_park to see a park's full activity list.
`stateCode`	No	Two-letter US state/territory code, or comma-separated list (e.g. "CA", "WY,MT,ID"). Filters to parks located in those states. Combine with query to narrow.

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The limit applied to this response (populated when results were truncated).
`error`	No	Present when the call failed. Absent on success.
`parks`	No	Matching parks, each carrying the parkCode needed to chain into the detail tools.
`shown`	No	Number of parks returned in this response (populated when the result set was capped by limit).
`notice`	No	Guidance on the result set: how to broaden a search that matched nothing, the start value for the next page when more parks matched, the way back when start ran past the end, and a best-effort disclosure when the activity scan could not cover every site.
`truncated`	No	True when more parks matched than this response returned; absent on a complete result.
`totalCount`	No	Total parks matching every filter, before start/limit were applied.
`appliedFilters`	No	Echo of the filters as applied (query / stateCode / activity).

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedSep 24, 2026

changedInput schema / properties / activity / description

Previous value: -"Filter to parks offering an activity, matched against each park's activities list (e.g. \"hiking\", \"camping\", \"stargazing\"). Case-insensitive substring match applied locally (the API has no activity param) across every site matching query/stateCode, then paginated with start/limit — so totalCount is the true count of matching parks, not a per-page tally. Use nps_get_park to see a park's full activity list."New value: +"Filter to parks offering an activity, matched against each park's activities list (e.g. \"hiking\", \"camping\", \"stargazing\"). Case-insensitive substring match, combined with query/stateCode and applied before start/limit, so totalCount counts every matching park, not one page. Use nps_get_park to see a park's full activity list."

changedInput schema / properties / query / description

Previous value: -"Free-text search across park names and descriptions (e.g. \"yosemite\", \"civil war\", \"redwood\"). Results are re-ranked locally so an exact parkCode or name match leads: NPS returns matches in alphabetical-by-code order with no relevance ranking, so without this the obvious park can sit behind sites that only mention the term in their description. Omit to browse by state. At least one of query or stateCode is recommended; with neither, returns the first page of all ~470 NPS sites."New value: +"Free-text search across park names and descriptions (e.g. \"yosemite\", \"civil war\", \"redwood\"). Exact parkCode or name matches lead, then other name matches, then parks that only mention the term in their description — ranked across every match before start/limit apply. Omit to browse by state. At least one of query or stateCode is recommended; with neither, returns the first page of all ~470 NPS sites."

changedOutput schema / properties / appliedFilters / description

Previous value: -"Echo of the filters as the server applied them (query / stateCode / activity), so the agent can see what was searched."New value: +"Echo of the filters as applied (query / stateCode / activity)."

changedOutput schema / properties / notice / description

Previous value: -"Guidance when no parks matched — suggests broadening the query, checking the state code, or dropping the activity filter."New value: +"Guidance on the result set: how to broaden a search that matched nothing, the start value for the next page when more parks matched, the way back when start ran past the end, and a best-effort disclosure when the activity scan could not cover every site."

changedOutput schema / properties / parks / items / properties / latitude / description

Previous value: -"Center latitude (decimal degrees), or null if the park record has no coordinates. Feed to nws-weather / open-meteo for a forecast."New value: +"Center latitude (decimal degrees), or null if the park record has no coordinates."

changedOutput schema / properties / parks / items / properties / url / description

Previous value: -"Park's official NPS.gov page — the source for everything trimmed from this summary."New value: +"Park's official NPS.gov page, with fuller detail than this summary."

changedOutput schema / properties / totalCount / description

Previous value: -"Total parks matching the query/state filter before the limit was applied."New value: +"Total parks matching every filter, before start/limit were applied."

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when more parks matched than this response returned; absent on a complete result.",
+  "type": "boolean"
+}

Changed6 schema fields changedSep 20, 2026
- removedOutput schema / properties / parks / items / properties / entranceFee / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / parks / items / properties / entranceFee / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / parks / items / properties / latitude / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / parks / items / properties / latitude / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / parks / items / properties / longitude / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / parks / items / properties / longitude / type
```
Added value: +[
+  "number",
+  "null"
+]
```

Changed6 schema fields changedAug 24, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / anyOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "parks",
+      "totalCount",
+      "appliedFilters"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `invalid_state_code`: A stateCode token is not two letters. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "invalid_state_code"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

removedOutput schema / required

Removed value: -[
-  "parks",
-  "totalCount",
-  "appliedFilters"
-]

Changed1 schema field changedJul 16, 2026
- removedInput schema / properties / stateCode / pattern
```
Removed value: -"^[A-Za-z]{2}(,[A-Za-z]{2})*$"
```

Changed2 schema fields changedJul 16, 2026

changedInput schema / properties / activity / description

Previous value: -"Filter to parks offering an activity, matched against each park's activities list (e.g. \"hiking\", \"camping\", \"stargazing\"). Case-insensitive substring match applied locally after fetch — it narrows the returned page, it does not search all ~470 sites by activity. Use nps_get_park to see a park's full activity list."New value: +"Filter to parks offering an activity, matched against each park's activities list (e.g. \"hiking\", \"camping\", \"stargazing\"). Case-insensitive substring match applied locally (the API has no activity param) across every site matching query/stateCode, then paginated with start/limit — so totalCount is the true count of matching parks, not a per-page tally. Use nps_get_park to see a park's full activity list."

changedInput schema / properties / query / description

Previous value: -"Free-text search across park names and descriptions (e.g. \"yosemite\", \"civil war\", \"redwood\"). Omit to browse by state. At least one of query or stateCode is recommended; with neither, returns the first page of all ~470 NPS sites."New value: +"Free-text search across park names and descriptions (e.g. \"yosemite\", \"civil war\", \"redwood\"). Results are re-ranked locally so an exact parkCode or name match leads: NPS returns matches in alphabetical-by-code order with no relevance ranking, so without this the obvious park can sit behind sites that only mention the term in their description. Omit to browse by state. At least one of query or stateCode is recommended; with neither, returns the first page of all ~470 NPS sites."

First observedJun 16, 2026

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds valuable context beyond these: it specifies the return payload (parkCode plus compact trip-planning summary) and the scope limitation (NPS sites only). It does not contradict the annotations and adds meaningful behavioral context, though it does not cover error handling or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exactly two sentences with zero redundancy. The first sentence front-loads the core purpose and workflow position; the second details the output and scope. Every word contributes to understanding, making it an exemplar of concise, structured documentation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and full parameter coverage in the schema, the description provides all necessary context for correct invocation. It explains the tool's role as the entry point, the nature of its output, and its coverage boundaries. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each of the 5 parameters thoroughly documented (e.g., query ranking order, stateCode format, limit/start semantics). The tool description itself does not add parameter-specific details beyond what the schema already provides; it only mentions the general output. This meets the baseline for full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('resolve') and resource ('place name, US state, or free-text query to National Park Service parks'). It clearly differentiates from siblings by identifying itself as the 'required first step before the detail tools' and noting that other tools depend on its parkCode. The explicit scope ('US NPS sites only') further distinguishes it from non-NPS park tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states it is the 'required first step before the detail tools', making its position in the workflow unambiguous. It also clarifies exclusions ('not state parks and not Forest Service or BLM land'), preventing misuse. While it doesn't name specific alternatives, the role as entry point and the coverage limitations provide clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All national-parks-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.