Skip to main content
Glama
Sign In

noaa-marine-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

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. Each call returns up to limit predictions starting at offset; when the range matched more, rows_matched, rows_returned, and next_offset 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

NameRequiredDescriptionDefault
datumNoDatum 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, whose hint names a datum to retry with.MLLW
limitNoPrediction rows to return on this page. Default 50; a larger value returns at most 1,000 and says so.
unitsNoUnit system for heights: english = feet; metric = meters.english
offsetNoRow offset into the matched prediction series, for reading a range longer than one page. 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_dateYesEnd date (inclusive), YYYYMMDD or YYYY-MM-DD, e.g. "20240607" or "2024-06-07".
intervalNoPrediction 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_zoneNoTime zone for returned timestamps. lst_ldt = local standard/daylight time (default); gmt = UTC; lst = local standard time year-round.lst_ldt
begin_dateYesStart date, YYYYMMDD or YYYY-MM-DD, e.g. "20240601" or "2024-06-01".
station_idYesCO-OPS tide station ID (numeric, e.g. "9447130" for Seattle). Obtain from noaa_marine_find_stations with types=["tide"].

Output Schema

NameRequiredDescriptionDefault
datumNoTidal datum used (e.g. MLLW) — echoed for correct interpretation of heights.
errorNoPresent when the call failed. Absent on success.
unitsNoHeight units: "english" (feet) or "metric" (meters).
noticeNoWhat this page of the prediction series covers and how to reach the next one, opening with the requested and applied values when limit was clamped to its cap. Present when the response is a page rather than the whole matched series, or limit was clamped.
truncatedNoTrue 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_idNoStation ID echoed from the request — for chaining.
next_offsetNoOffset 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_offsetNoRow offset this page starts at, echoed from the request. Absent when the whole matched series was returned.
predictionsNoTide predictions for the requested date range — up to limit rows starting at offset, and the whole series when it fits one page. rows_matched and next_offset report what a page left behind.
rows_matchedNoPrediction rows the requested date range matched, before the page was cut. Absent when the whole matched series was returned.
station_nameNoStation name as returned by CO-OPS — confirms the correct station was queried.
rows_returnedNoPrediction rows this page carries — the length of predictions. Absent when the whole matched series was returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • changedInput schema / properties / datum / description
      Previous 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."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, whose hint names a datum to retry with."
    • addedInput schema / properties / limit / default
      Added value: +50
    • changedInput schema / properties / limit / description
      Previous value: -"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."New value: +"Prediction rows to return on this page. Default 50; a larger value returns at most 1,000 and says so."
    • removedInput schema / properties / limit / maximum
      Removed value: -9007199254740991
    • addedInput schema / properties / limit / multipleOf
      Added value: +1
    • changedInput schema / properties / limit / type
      Previous value: -"integer"New value: +"number"
    • changedInput schema / properties / offset / description
      Previous value: -"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."New value: +"Row offset into the matched prediction series, for reading a range longer than one page. 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."
    • removedInput schema / properties / offset / maximum
      Removed value: -9007199254740991
    • addedInput schema / properties / offset / multipleOf
      Added value: +1
    • changedInput schema / properties / offset / type
      Previous value: -"integer"New value: +"number"
    • changedOutput schema / properties / notice / description
      Previous value: -"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."New value: +"What this page of the prediction series covers and how to reach the next one, opening with the requested and applied values when limit was clamped to its cap. Present when the response is a page rather than the whole matched series, or limit was clamped."
    • changedOutput schema / properties / predictions / description
      Previous 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."New value: +"Tide predictions for the requested date range — up to limit rows starting at offset, and the whole series when it fits one page. rows_matched and next_offset report what a page left behind."
  2. Changed1 schema field changed
    • 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. `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."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 or end_date is not a real calendar date, or the range starts after it ends. `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."
  3. Changed6 schema fields changed
    • 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"
+]
  4. Changed14 schema fields changed
    • 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"
+}
  5. Changed6 schema fields changed
    • 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"
-]
  6. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnly/idempotent/openWorld, so safety is covered; the description adds real behavioral context: a 1-year range cap, the subordinate_no_6min and datum_unavailable error shapes, and the offset-walking pagination contract. However, return format and pagination fields are largely restated rather than expanded, so it is useful but not exceptional beyond the annotations.

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

Conciseness4/5

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

Front-loaded with purpose, then failure modes, then pagination, then the prerequisite sibling call. It is a dense single block with some redundancy against the schema (the MLLW/datum explanation appears in both), but nearly every sentence carries operational information.

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?

With an output schema present, the description needn't explain return values, yet it still covers the pagination fields an agent must act on (rows_matched, rows_returned, next_offset). Combined with the prerequisite call, range cap, and error codes, an agent has everything needed to invoke correctly.

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 coverage is 100%, so the baseline is 3; the description adds marginal value by explaining that a year of events should be read by walking offset rather than splitting the range, and by tying interval choice to station type. Much of the datum and interval explanation duplicates the schema's own descriptions, so it does not substantially exceed the schema.

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?

Opens with a specific verb+resource+scope: high/low tide predictions for a CO-OPS tide station over a date range. It immediately distinguishes the two modes (hilo events vs 6-minute curve) and is clearly separable from siblings like noaa_marine_get_water_level or noaa_marine_find_stations.

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?

Explicitly routes the agent: 'Use noaa_marine_find_stations first to resolve a station name or location to a numeric station ID,' and names the alternative to consult (prediction_class on a find_stations tide row) before choosing interval=6min. It also states the fallback path when a subordinate station returns subordinate_no_6min.

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 toolsInspect
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.

Resources