noaa-marine-mcp-server

Get Tide Predictions

noaa_marine_get_tide_predictions

Read-onlyIdempotent

High and low tide predictions for a CO-OPS tide station over a date range. The default hilo interval returns the time, height, and tide type (H for high, L for low) of each event, while the 6-minute interval returns the detailed tide curve. Most tide stations are subordinate — CO-OPS derives their high and low events as offsets from a reference station and publishes no 6-minute curve for them — so interval="6min" reaches only a reference station, and a subordinate station comes back as subordinate_no_6min naming the reference station to ask instead; the prediction_class on a noaa_marine_find_stations tide row says which kind a station is before the call. Datum defaults to MLLW, mean lower low water, the standard for US nautical charts, and the date range is limited to 1 year per request. A range whose predictions fit the response budget is returned whole; a longer one is returned as a page of leading rows, and rows_matched, rows_returned, and next_offset then report how much matched and which offset reaches the rest, so a year of events is read by walking offset rather than by splitting the range. Use noaa_marine_find_stations first to resolve a station name or location to a numeric station ID.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`datum`	No	Datum the predicted heights are referenced to. MLLW (default) is the US nautical chart datum, and MHHW (mean higher high water) is the flooding reference; MHW, MTL, MSL, MLW, and DTL (diurnal tide level) are the other tidal planes. NAVD is NAVD88 and reads only where the station has an NAVD88 tie. STND is the station's own datum and is the plane that works where no tidal datum exists. CRD applies at Columbia River stations only. A datum this station does not carry comes back as datum_unavailable naming the ones it does.	MLLW
`limit`	No	Maximum prediction rows to return on this page, for a caller that wants fewer than the response budget allows. Omit for the largest page that fits; a value larger than the budget allows does not widen the page.
`units`	No	Unit system for heights: english = feet; metric = meters.	english
`offset`	No	Row offset into the matched prediction series, for reading a range whose rows do not fit one response. 0 (default) starts at the first row; pass the next_offset from a previous call to continue. An offset past the last row returns an empty page rather than an error.
`end_date`	Yes	End date (inclusive), YYYYMMDD or YYYY-MM-DD, e.g. "20240607" or "2024-06-07".
`interval`	No	Prediction interval: hilo (default) returns only high and low tide events; 6min returns a continuous prediction curve at 6-minute intervals, and is served only by a reference station — a subordinate station has no 6-minute curve.	hilo
`time_zone`	No	Time zone for returned timestamps. lst_ldt = local standard/daylight time (default); gmt = UTC; lst = local standard time year-round.	lst_ldt
`begin_date`	Yes	Start date, YYYYMMDD or YYYY-MM-DD, e.g. "20240601" or "2024-06-01".
`station_id`	Yes	CO-OPS tide station ID (numeric, e.g. "9447130" for Seattle). Obtain from noaa_marine_find_stations with types=["tide"].

Output Schema

TableJSON Schema

Name	Required	Description
`datum`	No	Tidal datum used (e.g. MLLW) — echoed for correct interpretation of heights.
`error`	No	Present when the call failed. Absent on success.
`units`	No	Height units: "english" (feet) or "metric" (meters).
`notice`	No	What this page of the prediction series covers and how to reach the next one. Present only when the response is a page rather than the whole matched series.
`truncated`	No	True when this page stops short of the last matched row, so further rows remain at next_offset. False on the final page and on a page past the end. Absent when the whole matched series was returned.
`station_id`	No	Station ID echoed from the request — for chaining.
`next_offset`	No	Offset to pass as offset on the next call, or null when this page reaches the last matched row. Absent when the whole matched series was returned.
`page_offset`	No	Row offset this page starts at, echoed from the request. Absent when the whole matched series was returned.
`predictions`	No	Tide predictions for the requested date range — the whole series when it fits one response, otherwise the leading page starting at offset. rows_matched and next_offset report what a page left behind.
`rows_matched`	No	Prediction rows the requested date range matched, before the page was cut. Absent when the whole matched series was returned.
`station_name`	No	Station name as returned by CO-OPS — confirms the correct station was queried.
`rows_returned`	No	Prediction rows this page carries — the length of predictions. Absent when the whole matched series was returned.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 22, 2026

changedInput schema / properties / begin_date / description

Previous value: -"Start date in YYYYMMDD format, e.g. \"20240601\"."New value: +"Start date, YYYYMMDD or YYYY-MM-DD, e.g. \"20240601\" or \"2024-06-01\"."

changedInput schema / properties / begin_date / pattern

Previous value: -"^\\d{8}$"New value: +"^(\\d{8}|\\d{4}-\\d{2}-\\d{2})$"

changedInput schema / properties / end_date / description

Previous value: -"End date in YYYYMMDD format (inclusive), e.g. \"20240607\"."New value: +"End date (inclusive), YYYYMMDD or YYYY-MM-DD, e.g. \"20240607\" or \"2024-06-07\"."

changedInput schema / properties / end_date / pattern

Previous value: -"^\\d{8}$"New value: +"^(\\d{8}|\\d{4}-\\d{2}-\\d{2})$"

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `station_not_found`: CO-OPS returned an error for the station ID — likely wrong type or invalid ID. `invalid_date_range`: begin_date/end_date is not a real calendar date or begin_date is after end_date `date_range_exceeded`: Requested date range exceeds the 1-year CO-OPS limit. `no_predictions`: Station exists but CO-OPS returned no prediction data for the date range. `subordinate_no_6min`: interval=\"6min\" was requested for a subordinate station, whose predictions are high and low events derived from a reference station. `datum_unavailable`: The station does not carry the requested datum — NAVD reads only where the station has an NAVD88 tie, and CRD only on the Columbia River. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `station_not_found`: CO-OPS returned an error for the station ID — likely wrong type or invalid ID. `invalid_date_range`: begin_date/end_date is not a real calendar date or begin_date is after end_date. `date_range_exceeded`: Requested date range exceeds the 1-year CO-OPS limit. `no_predictions`: Station exists but CO-OPS returned no prediction data for the date range. `subordinate_no_6min`: interval=\"6min\" was requested for a subordinate station, whose predictions are high and low events derived from a reference station. `datum_unavailable`: The station does not carry the requested datum — NAVD reads only where the station has an NAVD88 tie, and CRD only on the Columbia River. `upstream_throttled`: CO-OPS answered HTTP 403, which it returns for about two minutes while it throttles a burst of requests from one address. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "station_not_found",
-  "invalid_date_range",
-  "date_range_exceeded",
-  "no_predictions",
-  "subordinate_no_6min",
-  "datum_unavailable"
-]New value: +[
+  "station_not_found",
+  "invalid_date_range",
+  "date_range_exceeded",
+  "no_predictions",
+  "subordinate_no_6min",
+  "datum_unavailable",
+  "upstream_throttled"
+]

Changed14 schema fields changedSep 17, 2026

changedInput schema / properties / datum / description

Previous value: -"Tidal datum reference plane. MLLW (default) is the US nautical chart datum. MSL = mean sea level; MHHW = mean higher high water (flooding reference)."New value: +"Datum the predicted heights are referenced to. MLLW (default) is the US nautical chart datum, and MHHW (mean higher high water) is the flooding reference; MHW, MTL, MSL, MLW, and DTL (diurnal tide level) are the other tidal planes. NAVD is NAVD88 and reads only where the station has an NAVD88 tie. STND is the station's own datum and is the plane that works where no tidal datum exists. CRD applies at Columbia River stations only. A datum this station does not carry comes back as datum_unavailable naming the ones it does."

changedInput schema / properties / datum / enum

Previous value: -[
-  "MLLW",
-  "MHHW",
-  "MSL",
-  "MTL",
-  "MHW",
-  "MLW",
-  "CD",
-  "STND"
-]New value: +[
+  "MLLW",
+  "MHHW",
+  "MHW",
+  "MTL",
+  "MSL",
+  "MLW",
+  "DTL",
+  "NAVD",
+  "STND",
+  "CRD"
+]

changedInput schema / properties / interval / description

Previous value: -"Prediction interval: hilo (default) returns only high and low tide events; 6min returns a continuous prediction curve at 6-minute intervals."New value: +"Prediction interval: hilo (default) returns only high and low tide events; 6min returns a continuous prediction curve at 6-minute intervals, and is served only by a reference station — a subordinate station has no 6-minute curve."

addedInput schema / properties / limit

Added value: +{
+  "description": "Maximum prediction rows to return on this page, for a caller that wants fewer than the response budget allows. Omit for the largest page that fits; a value larger than the budget allows does not widen the page.",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Row offset into the matched prediction series, for reading a range whose rows do not fit one response. 0 (default) starts at the first row; pass the next_offset from a previous call to continue. An offset past the last row returns an empty page rather than an error.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `station_not_found`: CO-OPS returned an error for the station ID — likely wrong type or invalid ID. `invalid_date_range`: begin_date/end_date is not a real calendar date or begin_date is after end_date `date_range_exceeded`: Requested date range exceeds the 1-year CO-OPS limit. `no_predictions`: Station exists but CO-OPS returned no prediction data for the date range. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `station_not_found`: CO-OPS returned an error for the station ID — likely wrong type or invalid ID. `invalid_date_range`: begin_date/end_date is not a real calendar date or begin_date is after end_date `date_range_exceeded`: Requested date range exceeds the 1-year CO-OPS limit. `no_predictions`: Station exists but CO-OPS returned no prediction data for the date range. `subordinate_no_6min`: interval=\"6min\" was requested for a subordinate station, whose predictions are high and low events derived from a reference station. `datum_unavailable`: The station does not carry the requested datum — NAVD reads only where the station has an NAVD88 tie, and CRD only on the Columbia River. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "station_not_found",
-  "invalid_date_range",
-  "date_range_exceeded",
-  "no_predictions"
-]New value: +[
+  "station_not_found",
+  "invalid_date_range",
+  "date_range_exceeded",
+  "no_predictions",
+  "subordinate_no_6min",
+  "datum_unavailable"
+]

addedOutput schema / properties / next_offset

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Offset to pass as offset on the next call, or null when this page reaches the last matched row. Absent when the whole matched series was returned."
+}

addedOutput schema / properties / notice

Added value: +{
+  "description": "What this page of the prediction series covers and how to reach the next one. Present only when the response is a page rather than the whole matched series.",
+  "type": "string"
+}

addedOutput schema / properties / page_offset

Added value: +{
+  "description": "Row offset this page starts at, echoed from the request. Absent when the whole matched series was returned.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}

changedOutput schema / properties / predictions / description

Previous value: -"Tide predictions for the requested date range."New value: +"Tide predictions for the requested date range — the whole series when it fits one response, otherwise the leading page starting at offset. rows_matched and next_offset report what a page left behind."

addedOutput schema / properties / rows_matched

Added value: +{
+  "description": "Prediction rows the requested date range matched, before the page was cut. Absent when the whole matched series was returned.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}

addedOutput schema / properties / rows_returned

Added value: +{
+  "description": "Prediction rows this page carries — the length of predictions. Absent when the whole matched series was returned.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when this page stops short of the last matched row, so further rows remain at next_offset. False on the final page and on a page past the end. Absent when the whole matched series was returned.",
+  "type": "boolean"
+}

Changed6 schema fields changedAug 25, 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": [
+      "station_id",
+      "station_name",
+      "datum",
+      "units",
+      "predictions"
+    ]
+  },
+  {
+    "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: `station_not_found`: CO-OPS returned an error for the station ID — likely wrong type or invalid ID. `invalid_date_range`: begin_date/end_date is not a real calendar date or begin_date is after end_date `date_range_exceeded`: Requested date range exceeds the 1-year CO-OPS limit. `no_predictions`: Station exists but CO-OPS returned no prediction data for the date range. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "station_not_found",
+            "invalid_date_range",
+            "date_range_exceeded",
+            "no_predictions"
+          ],
+          "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: -[
-  "station_id",
-  "station_name",
-  "datum",
-  "units",
-  "predictions"
-]

First observedJun 7, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Even though the annotations already declare readOnly, idempotent, and openWorld hints, the description adds substantial behavioral context: subordinate_no_6min fallback naming the reference station, datum_unavailable responses for unsupported datums, the 1-year date-range cap, and response-budget pagination with rows_matched/rows_returned/next_offset. This goes far beyond what the structured annotations convey.

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 long but every sentence earns its place: core purpose, hilo vs. 6min behavior, subordinate-station exception, datum default, range limit, pagination behavior, and the find_stations prerequisite. It is front-loaded with the main purpose and then layers edge cases in a logical order without filler.

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?

For a 9-parameter tool with a rich schema and output schema, the description covers the non-obvious operational details an agent needs: how to reach reference vs. subordinate stations, how to page through long ranges, which datums are broadly usable, and how to obtain a station ID. The output schema handles return-field details, so nothing critical is missing.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3, but the description adds operational meaning beyond the schema: it explains that 6min only reaches reference stations, that MLLW is the nautical-chart standard, that the date range is capped at one year, and that offset walking is the intended pagination strategy. Some parameters like units and time_zone are left to the schema, but the schema already documents them well.

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 opens with a specific resource and action: 'High and low tide predictions for a CO-OPS tide station over a date range.' It immediately clarifies the two modes (hilo events vs. 6-minute curve) and the tide-type vocabulary (H/L), so an agent knows exactly what this tool returns and how it differs from observation-style sibling tools.

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

Usage Guidelines4/5

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

It gives explicit guidance to call noaa_marine_find_stations first to resolve a station ID, and clearly explains that interval='6min' only works for reference stations while subordinate stations must be queried at the named reference station. It does not explicitly contrast this tool with noaa_marine_get_water_level or noaa_marine_get_conditions, but the prediction-focused context and station prerequisite provide solid usage direction.

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

All noaa-marine-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.