Skip to main content
Glama

Server Details

NOAA SWPC space weather: storm scales, Kp index, aurora forecasts, solar wind, activity, alerts.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
cyanheads/noaa-spaceweather-mcp-server
GitHub Stars
1

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.5/5 across 6 of 6 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool targets a distinct aspect of space weather (alerts, aurora, conditions, Kp index, solar activity, solar wind). The descriptions clearly differentiate their purposes and even suggest when to use which tool, minimizing overlap.

Naming Consistency5/5

All tool names follow the consistent pattern `noaa_spaceweather_get_<resource>`, using snake_case and a clear verb-noun structure. There are no deviations or mixed conventions.

Tool Count5/5

With 6 tools, the server is well-scoped for a specialized domain. Each tool provides a necessary piece of information without bloat, and the number is sufficient to cover the main space weather data categories.

Completeness4/5

The tool set covers the primary space weather data: alerts, aurora forecasts, current conditions, Kp index, solar activity (flares, radiation), and solar wind. It is missing a dedicated geomagnetic storm forecast tool, but the Kp index and conditions tools cover the immediate needs. Overall, the surface is near-complete for its domain.

Available Tools

6 tools
noaa_spaceweather_get_alertsGet Space Weather AlertsA
Read-onlyIdempotent
Inspect

Active SWPC alerts, watches, and warnings — parsed into structured records with product type, NOAA scale and level, issue time, validity window, and plain text. Covers geomagnetic storms, radio blackouts, and radiation storms. With active_only=false, also returns informational summaries, expired notices, and cancellations. max_age_hours controls how far back to look (default 48 h); the SWPC feed keeps all historical records and has no built-in expiry.

ParametersJSON Schema
NameRequiredDescriptionDefault
active_onlyNoWhen true (default), return only in-force Warnings, Watches, and Alerts; exclude Summaries, Other, expired products, and cancellation notices. Set false to return all products, including cancellations (flagged by the cancelled field).
max_age_hoursNoMaximum age of alerts to return, in hours (default 48). The SWPC feed retains all historical records — this window prevents returning weeks of historical notices as "active."

Output Schema

ParametersJSON Schema
NameRequiredDescription
alertsYesMatching SWPC alert/watch/warning records.
noticeNoStatus notice when no alerts are active.
fetchedAtYesISO 8601 timestamp of when this data was fetched.
totalCountYesCount of records in the alerts array.
Behavior5/5

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint. The description adds valuable context: the SWPC feed retains all historical records with no built-in expiry, and max_age_hours controls the lookback window. No contradictions.

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?

Three sentences with clear front-loading of the core purpose. Every sentence provides essential information without redundancy. Efficient and well-structured.

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 tool with 2 optional parameters and an output schema, the description covers behavior, parameter rationale, and data types sufficiently. No gaps given the presence of output schema (return values not required).

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% (both parameters documented). The description reinforces parameter meaning by explaining the rationale for max_age_hours (preventing weeks of historical notices) and the effect of active_only. This adds value beyond 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?

The description clearly states the tool returns 'Active SWPC alerts, watches, and warnings' and specifies what it covers (geomagnetic storms, radio blackouts, radiation storms). It distinguishes itself from sibling tools like get_aurora_forecast or get_kp_index by focusing on alerts.

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?

The description explains behavior for active_only=true/false and mentions max_age_hours. While it doesn't explicitly state when to use this tool vs alternatives, the context signals (sibling tool names) and clear purpose make the usage context obvious.

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

noaa_spaceweather_get_aurora_forecastGet Aurora ForecastA
Read-onlyIdempotent
Inspect

OVATION model aurora forecast for the next ~30–60 min: global grid of aurora probability percentages by latitude/longitude (1° resolution). With optional coordinates, returns the local aurora probability at the nearest grid point, the minimum Kp needed for aurora at that latitude, and a plain-language go/no-go verdict. Without coordinates, returns only global metadata. Data updates every ~5 minutes. Coordinates are geographic (WGS84), not geomagnetic.

ParametersJSON Schema
NameRequiredDescriptionDefault
latitudeNoGeographic latitude in degrees (−90 to 90). Provide with longitude for a local aurora probability lookup.
longitudeNoGeographic longitude in degrees (−180 to 180). Provide with latitude for a local aurora probability lookup.

Output Schema

ParametersJSON Schema
NameRequiredDescription
localLookupYesLocal aurora lookup result. Null when no coordinates were provided.
forecastTimeYesTime the aurora forecast is valid for, ISO 8601.
gridPointCountYesTotal number of grid points in the OVATION model.
observationTimeYesTime of the OVATION model observation, ISO 8601.
topAuroraRegionYesApproximate region of the highest aurora probability grid point.
topAuroraPercentYesHighest aurora probability anywhere on the globe (0–100).
Behavior4/5

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

Annotations indicate read-only, open-world, idempotent. Description adds useful behavioral context: update frequency (~5 min), coordinate system (WGS84 geographic not geomagnetic), resolution (1° grid), and output behavior based on coordinates. No contradictions.

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?

Four sentences, front-loaded with main purpose, no unnecessary words. Each sentence adds essential information about behavior, modes, and data freshness.

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 tool has 2 optional params and output schema, description fully covers modes of operation, data source, update frequency, and coordinate system. No missing critical details for an AI agent to use the tool correctly.

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 coverage is 100% with descriptions. Description adds value by clarifying coordinate system (WGS84) and explaining that providing coordinates triggers local probability lookup with additional outputs like Kp needed and go/no-go verdict.

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?

Description clearly states it provides OVATION model aurora forecast for next 30-60 min with global grid of probability percentages. Distinguishes between local lookup with coordinates vs global metadata without. Differentiates from sibling tools (alerts, conditions, etc.) by focusing on aurora forecast.

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?

Explicitly states when to use each mode: provide coordinates for local probability, omit for global metadata. Mentions data updates every 5 minutes. Does not explicitly say when not to use, but sibling context provides differentiation.

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

noaa_spaceweather_get_conditionsGet Space Weather ConditionsA
Read-onlyIdempotent
Inspect

Current space-weather snapshot: NOAA R/S/G storm scales (today + 3-day forecast), latest Kp index with its G-scale equivalent and aurora-visibility latitude, and a plain-language status summary. The quickest way to answer "is anything happening right now?" — use before deciding whether to drill into solar wind (noaa_spaceweather_get_solar_wind), aurora (noaa_spaceweather_get_aurora_forecast), or alert details (noaa_spaceweather_get_alerts).

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
todayYesCurrent observed NOAA storm scales for today.
summaryYesPlain-language status summary suitable for display, e.g. "Quiet conditions" or "G2 moderate geomagnetic storm in progress."
forecastYes3-day NOAA scale forecast (next 1–3 days).
currentKpYesLatest observed planetary K-index (0–9).
observedAtYesUTC date and time of the NOAA scales data period this snapshot reflects, e.g. "2026-06-04 15:00:00".
currentGScaleYesNOAA G-scale equivalent for current Kp (0–5).
auroraLatitudeYesAurora visibility guidance for current conditions, e.g. "Aurora possible to ~55° geomagnetic latitude".
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. Description adds useful behavioral context: includes forecasts, plain-language summary, and that it's a snapshot. No contradiction.

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?

Two sentences concisely communicate purpose, content, and usage guidance. No redundant or irrelevant 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?

Tool has zero parameters and an output schema, so description need not explain return values. It fully covers what the tool does and when to use it, making it complete for an AI agent.

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?

No parameters exist, so description correctly does not add parameter info. Baseline of 4 is appropriate as schema coverage is 100% and no parameter documentation is needed.

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?

Description clearly states it provides a 'current space-weather snapshot' with specific data elements (R/S/G scales, Kp index, aurora latitude) and explicitly distinguishes from sibling tools by naming them and their purposes.

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 states it is 'the quickest way to answer "is anything happening right now?"' and advises to 'use before deciding whether to drill into' sibling tools like solar wind, aurora forecast, and alerts.

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

noaa_spaceweather_get_kp_indexGet Kp IndexA
Read-onlyIdempotent
Inspect

Planetary K-index (0–9 geomagnetic activity scale) — recent observed 3-hour values with their NOAA G-scale equivalents and aurora-latitude guidance, plus the 3-day Kp forecast series. Kp is the primary driver of aurora visibility and geomagnetic storm severity: Kp≥5 is G1, Kp≥7 is G3 (aurora to ~50°), Kp≥9 is G5 extreme. Use noaa_spaceweather_get_conditions for a combined snapshot including storm scales; use this tool when you need the Kp time series or forecast detail.

ParametersJSON Schema
NameRequiredDescriptionDefault
window_daysNoNumber of past days of observed Kp to return (1–7, default 1). Larger windows show trend context.

Output Schema

ParametersJSON Schema
NameRequiredDescription
forecastYesForward-looking Kp forecast series (estimated and predicted entries only; observed history excluded).
observedYesObserved Kp readings within the requested window, oldest first.
currentKpYesLatest observed Kp value.
currentGScaleYesNOAA G-scale for current Kp.
observedCountYesNumber of Kp observations in the observed array, matching the requested window.
auroraLatitudeYesAurora visibility guidance for current conditions.
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint. The description adds valuable behavioral context: explaining the Kp scale and its relationship to G-storms and aurora visibility, which helps the agent understand the tool's output implications.

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 only two sentences, front-loading the key information about what the tool returns and then providing usage guidance. Every sentence adds value with no redundancy.

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

Completeness4/5

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

For a simple tool with one parameter and an output schema, the description covers the essential aspects: output content, scale interpretation, usage guidance. It could mention the forecast timescale, but overall it's sufficiently complete.

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% for the single parameter window_days, which already describes its purpose. The description does not add significant extra meaning beyond the schema, so baseline score of 3 is appropriate.

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 clearly states the tool returns the Planetary K-index with observed 3-hour values, G-scale equivalents, aurora-latitude guidance, and 3-day forecast. It explicitly distinguishes from sibling tool noaa_spaceweather_get_conditions by specifying when to use each.

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 provides explicit guidance: 'Use noaa_spaceweather_get_conditions for a combined snapshot...; use this tool when you need the Kp time series or forecast detail.' This clearly tells the agent when to use this tool vs the alternative.

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

noaa_spaceweather_get_solar_activityGet Solar ActivityA
Read-onlyIdempotent
Inspect

Solar flare and radiation storm picture: recent GOES X-ray flux with flare-class labels (A/B/C/M/X), 3-day flare-class probabilities (C/M/X), active solar regions with per-region flare probabilities, and GOES integral proton flux at ≥10 MeV with NOAA S-scale. For operators tracking HF radio blackout (R-scale, driven by X-ray) and radiation storm risk (S-scale, driven by protons). Active region data helps identify which region is driving current activity.

ParametersJSON Schema
NameRequiredDescriptionDefault
include_regionsNoInclude active solar region details (default true). Set false to skip region data and reduce response size.

Output Schema

ParametersJSON Schema
NameRequiredDescription
sScaleYesCurrent NOAA S-scale for solar radiation storms (0–5), derived from latest proton flux.
fetchedAtYesISO 8601 timestamp of when this data was fetched.
latestXrayYesMost recent GOES X-ray flux reading, null if unavailable.
recentXrayYesGOES X-ray flux readings from the past hour, oldest first.
sScaleTextYesPlain-language S-scale description, e.g. "S2 moderate radiation storm".
latestProtonYesMost recent ≥10 MeV proton flux reading, null if unavailable.
activeRegionsYesCurrently active solar regions with per-region flare probabilities. Empty when include_regions=false or no regions are active.
probabilitiesYes3-day flare probability forecasts.
Behavior4/5

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

Annotations already declare readOnlyHint=true, so safety is covered. Description adds value by detailing the data components (X-ray flux, flare classes, proton flux, active regions) and the scales (R-scale, S-scale), which helps the agent understand the tool's behavioral scope without repeating 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?

Description is concise at three sentences, front-loading the main output and use case. Each sentence adds relevant information; no wasted words, though it could be slightly tighter.

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

Completeness4/5

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

Given the complexity of solar activity data and the presence of an output schema, the description covers the key elements: flare and radiation storm metrics, active regions, and the operator use case. It is sufficient for an agent to understand what the tool offers.

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% for the single parameter include_regions, and its description in the schema is already clear. The tool description does not add extra meaning beyond what the schema provides, so it meets the baseline of 3.

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?

Description clearly states the tool provides a 'solar flare and radiation storm picture' including specific data like GOES X-ray flux, flare probabilities, active regions, and proton flux. The verb 'get' and resource 'solar activity' are specific, and it distinguishes from siblings (e.g., no other tool mentions flare or proton data).

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?

Description explicitly targets 'operators tracking HF radio blackout and radiation storm risk,' providing clear context of use. It does not explicitly state when not to use or name alternatives, but sibling tools offer contrasting options (e.g., aurora forecast, KP index), implying situational differentiation.

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

noaa_spaceweather_get_solar_windGet Solar WindA
Read-onlyIdempotent
Inspect

Real-time solar wind measurements from the active spacecraft at L1: proton speed (km/s), density (n/cm³), temperature (K), and the critical Bz component (southward Bz = negative = storm driver). Returns the recent plasma and magnetic field time series within the requested window, oldest first, each record tagged with the reporting spacecraft. Bz < −10 nT for sustained periods is a primary geomagnetic storm trigger — use alongside noaa_spaceweather_get_kp_index to see whether elevated solar wind has translated into a geomagnetic storm.

ParametersJSON Schema
NameRequiredDescriptionDefault
window_hoursNoHours of recent solar wind history to return (1–168, default 3). Records update ~every 1 min, but the feed only carries roughly the last 24 hours — a larger window returns the whole feed, not more history. When a window comes back empty, feedStalenessHours and latestFeedPlasmaTime/latestFeedMagTime report how current the feed actually is.

Output Schema

ParametersJSON Schema
NameRequiredDescription
magYesMagnetic field measurements (Bx, By, Bz, Bt) within the window, oldest first.
noticeNoGuidance when the requested window returned no plasma or magnetic field records — names the newest record the feed carries, or reports that the feed itself returned nothing from an active spacecraft.
plasmaYesPlasma measurements (speed, density, temperature) within the window, oldest first.
bzStatusYesPlain-language Bz status, e.g. "Southward Bz −14 nT — storm-driving conditions" or "Northward Bz +5 nT — quiescent".
magCountYesNumber of magnetic field records in the mag array, spanning the requested window.
latestMagYesMost recent magnetic field reading, null if no data in window.
plasmaCountYesNumber of plasma records in the plasma array, spanning the requested window.
latestPlasmaYesMost recent plasma reading, null if no data in window.
latestFeedMagTimeYesISO 8601 time of the newest magnetic field record the feed carries, ignoring the window. Null when the feed returned no active-spacecraft mag records.
feedStalenessHoursYesHours between now and the newest record across both feeds — how far behind real time the upstream data is. Null when both feeds returned no active-spacecraft records.
latestFeedPlasmaTimeYesISO 8601 time of the newest plasma record the feed carries, ignoring the window. Null when the feed returned no active-spacecraft plasma records. Compare against the window to tell a quiet feed from a stale one.
Behavior5/5

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

Annotations declare readOnlyHint=true and idempotentHint=true, which the description does not contradict. The description adds significant behavioral context: returns time series oldest first, records tagged with spacecraft, feed update frequency (every ~1 min), feed window limitation (last 24 hours), and the significance of Bz < -10 nT as a storm trigger. This goes well beyond 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?

The description is moderately sized (4 sentences), well-structured, and front-loaded with key measurements. Every sentence adds value, though the trigger sentence could be seen as additional context rather than essential. Overall efficient.

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 input schema fully covers the single parameter, annotations provide behavioral hints, an output schema exists (so return values are explained externally), and the description explains usage triggers and feed behavior, the tool definition is complete and well-rounded for an AI agent.

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

Parameters5/5

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

Input schema has 100% coverage for the single parameter window_hours, already described. The description adds extra semantic value: explains that larger windows return the whole feed rather than more history, that records update every ~1 min, and provides guidance on handling empty windows via staleness fields. This enriches the schema's basic description.

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 clearly states the tool retrieves real-time solar wind measurements from L1, listing specific parameters (proton speed, density, temperature, Bz). It distinguishes itself from siblings by focusing on plasma and magnetic field data, and is not a tautology.

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?

The description explicitly suggests using alongside noaa_spaceweather_get_kp_index to assess whether elevated solar wind has translated into a geomagnetic storm. It provides clear context but does not state when not to use this tool, though the pairing recommendation is strong.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.