com.gribstream/mcp

Est-ce que com.gribstream/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.gribstream/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 12 outils

• gribstream_build_runs_request≈ 2131 tokens

  NO AUTH / PUBLIC / READ-ONLY. Build and validate a runnable /runs API request and curl command without sending it. Use gribstream_query_runs to retrieve model-run comparisons directly; a separate build call is optional. Use catalog selectors in request.variables and points in request.coordinates or one request.grid.

  Paramètres, retour & exemple (3)

  Paramètres

  • accept · string · optionnel · text/csv | application/json | application/ndjson | application/x-ndjson | application/vnd.apache.parquet | application/x-parquet | application/parquet
    Desired response format for the eventual HTTP request. Prefer application/vnd.apache.parquet for dense grids and large typed tabular results.
  • dataset · string · requis
    Dataset code, for example gfs, ifsoper, nbm, hrrr, or urma.
  • request · object · requis
    Runs request body. Use timesList for exact UTC model run times, or the half-open range forecastedFrom+forecastedUntil where forecastedFrom is inclusive, forecastedUntil is exclusive, and forecastedFrom must be earlier than forecastedUntil. Equal bounds select no times. Coordinates must be in request.coordinates, and variable selectors must be in request.variables.

  Exemple d'appel

  {"name": "gribstream_build_runs_request", "arguments": {"dataset": "texte", "request": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "body": {}, "curl": "texte", "valid": true, "errors": [], "method": "texte", "headers": {}, "endpoint": "timeseries", "warnings": [], "timestamp_semantics": "texte"}}

• gribstream_build_timeseries_request≈ 2164 tokens

  NO AUTH / PUBLIC / READ-ONLY. Build and validate a runnable /timeseries API request and curl command without sending it. Use gribstream_query_timeseries to retrieve data directly; a separate build call is optional. Use catalog selectors in request.variables and points in request.coordinates or one request.grid. Omit asOf for latest forecasts.

  Paramètres, retour & exemple (3)

  Paramètres

  • accept · string · optionnel · text/csv | application/json | application/ndjson | application/x-ndjson | application/vnd.apache.parquet | application/x-parquet | application/parquet
    Desired response format for the eventual HTTP request. Prefer application/vnd.apache.parquet for dense grids and large typed tabular results.
  • dataset · string · requis
    Dataset code, for example gfs, ifsoper, nbm, hrrr, or urma.
  • request · object · requis
    Timeseries request body. Use timesList for exact UTC valid times, or the half-open range fromTime+untilTime where fromTime is inclusive, untilTime is exclusive, and fromTime must be earlier than untilTime. Equal bounds select no times. Omit asOf unless the user explicitly asks for backtesting, time travel, what was known then, or a historical model-run cutoff. Coordinates must be in request.coordinates, and variable selectors must be in request.variables.

  Exemple d'appel

  {"name": "gribstream_build_timeseries_request", "arguments": {"dataset": "texte", "request": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "body": {}, "curl": "texte", "valid": true, "errors": [], "method": "texte", "headers": {}, "endpoint": "timeseries", "warnings": [], "timestamp_semantics": "texte"}}

• gribstream_get_dataset≈ 188 tokens

  NO AUTH / PUBLIC / READ-ONLY. Inspect archive coverage, cadence, horizon, members, and native_grid geometry for one dataset. The native coordinate URL requires authentication and geographic bounds; geometry does not prove variable availability.

  Paramètres, retour & exemple (1)

  Paramètres

  • dataset · string · requis
    Dataset code, for example gfs, nbm, ifsoper, hrrr, urma.

  Exemple d'appel

  {"name": "gribstream_get_dataset", "arguments": {"dataset": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• gribstream_get_expression_reference≈ 144 tokens

  NO AUTH / PUBLIC / READ-ONLY. Get expression syntax, alias rules, examples, and supported func.* math functions for derived weather signals.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "gribstream_get_expression_reference", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• gribstream_get_parameter≈ 241 tokens

  NO AUTH / PUBLIC / READ-ONLY. Gets detailed metadata and exact selector variations for one already-known dataset-native parameter code. Parameter codes are case-sensitive. For a common natural-language concept such as 2 metre temperature, use gribstream_resolve_shared_parameter before guessing a native code.

  Paramètres, retour & exemple (2)

  Paramètres

  • dataset · string · requis
    Dataset code, for example ifsoper.
  • parameter · string · requis
    Exact case-sensitive parameter short name, for example 100u, 2t, TMP, or APCP.

  Exemple d'appel

  {"name": "gribstream_get_parameter", "arguments": {"dataset": "texte", "parameter": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• gribstream_list_datasets≈ 746 tokens

  NO AUTH / PUBLIC / READ-ONLY. Find candidate datasets for a region and weather variable. Filter by provider, region, forecast_time, shared_parameter and is_ensemble; sort_by=resolution ranks nominal resolution in km. With shared_parameter, each result includes a validated request fragment and exact/approximate match. Use it directly in one gribstream_query_timeseries call. Coverage envelopes and forecast horizons are catalog hints, not live availability guarantees. No weather values are fetched.

  Paramètres, retour & exemple (10)

  Paramètres

  • tag · ? · optionnel
    Tag or list of tags. Multiple tags use AND semantics in the API.
  • code · ? · optionnel
    Dataset code or list of dataset codes, for example gfs or ["gfs", "ifsoper"].
  • limit · integer · optionnel
    Maximum candidates to return; omit to inspect alternatives including unknown coverage.
  • family · string · optionnel
    Dataset family filter, for example gfs, ifs, nbm, hrrr, rap, rtma, urma.
  • region · object · optionnel
  • sort_by · string · optionnel · resolution
    Sort candidates by nominal source resolution, finest first; unknown coverage/resolution sorts last. Read coverage_kind before claiming a winner.
  • provider · string · optionnel
    Case-insensitive provider substring, e.g. Met Office, ECMWF, NOAA, DWD.
  • is_ensemble · boolean · optionnel
    Filter to ensemble datasets when true, or deterministic datasets when false.
  • forecast_time · string · optionnel
    Optional RFC3339 valid time with offset, e.g. 2026-10-16T12:00:00-03:00. Response normalizes to UTC. Filters nominal horizon, not live run availability. Resolve place and local timezone first; never assume local noon is UTC noon.
  • shared_parameter · string · optionnel
    Weather concept code, e.g. temperature_2m. Return only validated equivalents, including request fragments and approximation labels.

  Exemple d'appel

  {"name": "gribstream_list_datasets", "arguments": {"tag": "texte", "code": "texte", "limit": 1, "family": "texte", "region": {}, "sort_by": "resolution"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"datasets": []}}

• gribstream_list_parameters≈ 194 tokens

  NO AUTH / PUBLIC / READ-ONLY. Lists parameter summaries for one dataset. Use this before selecting exact case-sensitive parameter codes.

  Paramètres, retour & exemple (1)

  Paramètres

  • dataset · string · requis
    Dataset code, for example ifsoper.

  Exemple d'appel

  {"name": "gribstream_list_parameters", "arguments": {"dataset": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"parameters": []}}

• gribstream_list_shared_parameters≈ 298 tokens

  NO AUTH / PUBLIC / READ-ONLY. Lists normalized shared parameter presets that can map one logical signal across datasets. Use this only when the shared parameter code is uncertain; when a common code such as temperature_2m is already clear, call gribstream_resolve_shared_parameter directly.

  Paramètres, retour & exemple (2)

  Paramètres

  • dataset · ? · optionnel
    Optional dataset code or list of dataset codes to filter supported shared parameters.
  • dataset_mode · string · optionnel · any | all
    Whether every listed dataset must support the preset or any one may support it.

  Exemple d'appel

  {"name": "gribstream_list_shared_parameters", "arguments": {"dataset": "texte", "dataset_mode": "any"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"shared_parameters": []}}

• gribstream_query_runs≈ 3768 tokens

  AUTH REQUIRED / DATA QUERY. Fetch or retrieve weather values across model runs to compare changing forecasts. timesList selects exact model run times, not valid times; minHorizon/maxHorizon constrain lead hours. Use discovered request.variables with coordinates or one grid. CSV is the default; use delivery=url for large results. Response rows are unsorted; sort by location, forecasted_at and forecasted_time before plotting. When a live query returns a resource_link, the exact signed HTTPS URL is the result: download it directly once with an available HTTPS or file-download capability, without an API token. This consumes the selected GribStream MCP result; it is not a direct GribStream API call or a connector bypass. Do not look for an MCP resources/read tool, and do not repeat the query merely to obtain the file bytes.

  Paramètres, retour & exemple (5)

  Paramètres

  • accept · string · optionnel · text/csv | application/json | application/ndjson | application/x-ndjson | application/vnd.apache.parquet | application/x-parquet | application/parquet
    Desired response format. Defaults to text/csv for compatibility. For dense grids and large tabular analysis, use application/vnd.apache.parquet only when a compatible reader is already known to be available. If reader availability is unknown, do not probe or install packages; use text/csv with delivery=url immediately.
  • dataset · string · requis
    Dataset code, for example gfs, ifsoper, nbm, hrrr, or urma.
  • request · object · requis
    Runs request body. Use timesList for exact UTC model run times, or the half-open range forecastedFrom+forecastedUntil where forecastedFrom is inclusive, forecastedUntil is exclusive, and forecastedFrom must be earlier than forecastedUntil. Equal bounds select no times. Coordinates must be in request.coordinates, and variable selectors must be in request.variables.
  • delivery · string · optionnel · inline | url
    Optional result delivery mode. Set inline for CSV, JSON, or NDJSON in the MCP result, or url for a short-lived signed resource link. Omission defaults to inline for text formats; Parquet always uses URL delivery and rejects delivery=inline. For a resource_link blocked by client network policy, do not retry URL delivery: if a text artifact is at most 10000000 bytes, retry the same request at most once with delivery=inline; otherwise reduce it using the documented split order first.
  • max_bytes · integer · optionnel
    Maximum inline response bytes to return through MCP for CSV/JSON/NDJSON. Default and server-side maximum are 10000000. This setting does not limit artifacts delivered by signed URL. For dense grids or large tabular results, use delivery=url so MCP returns a short-lived signed HTTPS resource link instead of putting the full dataset into tool output. Prefer application/vnd.apache.parquet only when a compatible Parquet reader is already known to be available. If reader availability is unknown, do not spend tool calls probing or installing packages; use text/csv with delivery=url immediately. Use one grid request, process the downloaded file locally, and never print or serialize the full file into chat or tool output. Do not install a dependency or write a Parquet parser solely for one result. When a real API request limit requires splitting, split by time range first, split variables second, and split coordinates/grid/space last; spatial tiling creates the most extra work.

  Exemple d'appel

  {"name": "gribstream_query_runs", "arguments": {"dataset": "texte", "request": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"uri": "texte", "data": [], "rows": 1, "bytes": 1, "binary": true, "schema": [], "columns": [], "dataset": "texte", "preview": "texte", "delivery": "texte", "endpoint": "texte", "cache_hit": true}}

• gribstream_query_timeseries≈ 3825 tokens

  AUTH REQUIRED / DATA QUERY. Fetch or retrieve weather values for maps, heatmaps and analysis at selected valid times. Use discovered request.variables with coordinates or one grid; no separate build/validate call is needed. CSV is the default; use delivery=url for large results and render the downloaded file locally. Prefer Parquet only with an available reader. Use timesList for one exact UTC valid time; omit asOf for latest forecasts. Requested sampling does not increase native resolution. Response rows are unsorted; sort rows before plotting. When a live query returns a resource_link, the exact signed HTTPS URL is the result: download it directly once with an available HTTPS or file-download capability, without an API token. This consumes the selected GribStream MCP result; it is not a direct GribStream API call or a connector bypass. Do not look for an MCP resources/read tool, and do not repeat the query merely to obtain the file bytes.

  Paramètres, retour & exemple (5)

  Paramètres

  • accept · string · optionnel · text/csv | application/json | application/ndjson | application/x-ndjson | application/vnd.apache.parquet | application/x-parquet | application/parquet
    Desired response format. Defaults to text/csv for compatibility. For dense grids and large tabular analysis, use application/vnd.apache.parquet only when a compatible reader is already known to be available. If reader availability is unknown, do not probe or install packages; use text/csv with delivery=url immediately.
  • dataset · string · requis
    Dataset code, for example gfs, ifsoper, nbm, hrrr, or urma.
  • request · object · requis
    Timeseries request body. Use timesList for exact UTC valid times, or the half-open range fromTime+untilTime where fromTime is inclusive, untilTime is exclusive, and fromTime must be earlier than untilTime. Equal bounds select no times. Omit asOf unless the user explicitly asks for backtesting, time travel, what was known then, or a historical model-run cutoff. Coordinates must be in request.coordinates, and variable selectors must be in request.variables.
  • delivery · string · optionnel · inline | url
    Optional result delivery mode. Set inline for CSV, JSON, or NDJSON in the MCP result, or url for a short-lived signed resource link. Omission defaults to inline for text formats; Parquet always uses URL delivery and rejects delivery=inline. For a resource_link blocked by client network policy, do not retry URL delivery: if a text artifact is at most 10000000 bytes, retry the same request at most once with delivery=inline; otherwise reduce it using the documented split order first.
  • max_bytes · integer · optionnel
    Maximum inline response bytes to return through MCP for CSV/JSON/NDJSON. Default and server-side maximum are 10000000. This setting does not limit artifacts delivered by signed URL. For dense grids or large tabular results, use delivery=url so MCP returns a short-lived signed HTTPS resource link instead of putting the full dataset into tool output. Prefer application/vnd.apache.parquet only when a compatible Parquet reader is already known to be available. If reader availability is unknown, do not spend tool calls probing or installing packages; use text/csv with delivery=url immediately. Use one grid request, process the downloaded file locally, and never print or serialize the full file into chat or tool output. Do not install a dependency or write a Parquet parser solely for one result. When a real API request limit requires splitting, split by time range first, split variables second, and split coordinates/grid/space last; spatial tiling creates the most extra work.

  Exemple d'appel

  {"name": "gribstream_query_timeseries", "arguments": {"dataset": "texte", "request": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"uri": "texte", "data": [], "rows": 1, "bytes": 1, "binary": true, "schema": [], "columns": [], "dataset": "texte", "preview": "texte", "delivery": "texte", "endpoint": "texte", "cache_hit": true}}

• gribstream_resolve_shared_parameter≈ 308 tokens

  NO AUTH / PUBLIC / READ-ONLY. Resolves a weather concept to validated native variables/expressions and an exact or approximate match label. Use resolved_request directly in /timeseries or /runs; read resolved_match for height differences and native statistics. Use this first for common natural-language concepts such as 2 metre temperature or 10 metre wind instead of guessing dataset-native codes such as TMP.

  Paramètres, retour & exemple (3)

  Paramètres

  • alias · string · optionnel
    Optional output alias for the resolved request.
  • dataset · string · optionnel
    Optional dataset code to resolve the shared parameter against.
  • parameter · string · requis
    Shared parameter code, for example temperature_2m, wind_speed_10m, mean_sea_level_pressure, or wind_speed_500hpa.

  Exemple d'appel

  {"name": "gribstream_resolve_shared_parameter", "arguments": {"parameter": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• gribstream_validate_request≈ 1894 tokens

  NO AUTH / PUBLIC / READ-ONLY. Validates the basic shape, exact selector tuples, and expression syntax of a proposed GribStream /timeseries or /runs request without sending it. Use this before returning any hand-edited curl or when changing a request from one dataset to another.

  Paramètres, retour & exemple (3)

  Paramètres

  • dataset · string · requis
    Dataset code, for example gfs, ifsoper, nbm, hrrr, or urma.
  • request · object · requis
    Request body to validate. Omit asOf unless the user explicitly asks for backtesting, time travel, what was known then, or a historical model-run cutoff for /timeseries. Use request.coordinates for point coordinates and request.variables for variable selectors.
  • endpoint · string · requis · timeseries | runs
    Endpoint to validate.

  Exemple d'appel

  {"name": "gribstream_validate_request", "arguments": {"dataset": "texte", "request": {}, "endpoint": "timeseries"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"valid": true, "errors": [], "dataset": "texte", "endpoint": "timeseries", "warnings": [], "timestamp_semantics": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://gribstream.com/mcp