com.hydrata/hydrata-mcp-server

Est-ce que com.hydrata/hydrata-mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.hydrata/hydrata-mcp-server » 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 28 outils

• add_observation_photo_link≈ 375 tokens

  Attach a photo to a flood observation as a reference LINK (never a file). MCP never uploads photo bytes. A local path, file:// URL or data: URI is refused: to upload a photo file, open the observation in the map and use the photo strip on its form (JPEG, PNG or HEIC, 25 MB, 10 per observation). The link counts toward the 10.

  Paramètres, retour & exemple (7)

  Paramètres

  • fid · integer · requis
    The observation's fid
  • credit · string · optionnel
    Who took it / the rights holder (optional)
  • caption · string · optionnel
    What the photo shows (optional, up to 500 characters)
  • layer_id · integer · requis
    The flood observation layer id
  • project_id · integer · requis
    The project ID
  • reference_url · string · requis
    An http(s) link to the photo (stored, never fetched)
  • public_consent · boolean · optionnel
    Show this photo to visitors of a public project (default false: members only)

  Exemple d'appel

  {"name": "add_observation_photo_link", "arguments": {"fid": 1, "layer_id": 1, "project_id": 1, "reference_url": "texte"}}

  Exemple de retour

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

• add_observations≈ 668 tokens

  Add flood observations (Flood mark, Timed level, Gauge record, Dry point) to a layer. POSTs each observation to /projects/<id>/flood-observations/<layer>/observations/ in order. The API validates every field: a row it refuses (400) is listed in `rejected` with its `problems` and the rest still land; a refusal that is not about the row (403 not an Editor, 404, 409) stops the batch and is reported in `stopped`, with `not_sent_count`. Stages are on the LAYER's vertical datum. Photos are not part of an observation: attach a link with add_observation_photo_link.

  Paramètres, retour & exemple (5)

  Paramètres

  • srid · ? · optionnel
    EPSG code for every geometry that does not carry its own `srid` (the projected CRS its eastings/northings are in, e.g. a UTM zone); omit for [lon, lat] (EPSG:4326)
  • layer_id · integer · requis
    The flood observation layer id (create_observation_layer / list_observations)
  • project_id · integer · requis
    The project ID
  • observations · array · requis
    Observations, each the API write body: subtype (flood_mark | timed_level | gauge_record | dry_point), name (required: a short label, e.g. the survey mark id), geometry {type: Point, coordinates: [lon, lat]} (or native x/y with srid), value_kind (stage | depth) + stage_m or depth_m, uncertainty_grade (H/M/L) or uncertainty_m, bound (exact | at_least | at_most), observed_start/observed_end (ISO 8601; naive times read in entry_timezone, by default the project's own zone), mark_type, flood_name, source, licence, notes; a flood_mark or dry_point must say which flood it is: a date window (observed_start / observed_end) or flood_name (ask the user; never guess a date); a gauge_record needs data_timeseries_id (+ gauge_zero_m). At most 200 per call
  • entry_timezone · ? · optionnel
    IANA zone for naive observed_start/observed_end on rows that do not carry their own entry_timezone; omit to use the project's zone (derived from where the project is, reported back as entry_timezone). Give it only when the times were read elsewhere

  Exemple d'appel

  {"name": "add_observations", "arguments": {"layer_id": 1, "project_id": 1, "observations": []}}

  Exemple de retour

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

• attach_input_layer≈ 1184 tokens

  Attach a GeoJSON you uploaded to GeoNode as the project's boundary, friction, inflow, rainfall, building, mesh_region or culvert layer. The agent moves the bytes: first upload the GeoJSON yourself, with the same credential, to GeoNode's upload endpoint at the site origin: curl -sS -u <user>:<password> -F "base_file=@/path/rainfall.geojson" https://<site>/api/v2/uploads/upload/ → JSON with `execution_id`. Then call this tool with it. The tool polls GET /api/v2/resource-service/execution-status/<execution_id> (bounded by timeout_seconds; statuses ready → running → finished | failed), reads the new dataset's pk, and PATCHes it onto the project's DEFAULT row of that kind ('Boundary 01' … 'MeshRegion 01' — the six rows the terrain import seeds ~30 s after get_terrain reports ready; if the list is still empty the tool says so: run finalize_terrain_upload / wait for get_terrain first). kind `culvert` (Hydraulic Structures; one two-point line per culvert, Inlet first, then Outlet): no culvert row is seeded, so the tool creates 'Culvert 01' when the project has none and waits for its layer. It reads your culverts back and maps your attribute names onto the culvert fields — name, shape (box|circular), width_m, height_m, diameter_m, upstream_invert_m, downstream_invert_m, barrels (1-20), wall_thickness_m, entrance_type, material (concrete|corrugated_metal), manning_n, blockage_pct (Reduced-area blockage, percent), length_override_m, description — accepting common alternatives (width, diameter, label, us_invert, ds_invert, num_barrels, manning, blockage, length, shape 'pipe' = circular, …) and filling the defaults (barrels 1, wall 0.20 m, square_edge_headwall, concrete, manning_n from the material, blockage 0). Other attributes are kept. If anything changed it re-uploads the mapped culverts and attaches THAT layer (`mapped`: renamed, filled, source_dataset_pk). `culvert_problems` lists what the build will still refuse (typically missing inverts) — the user fixes those in the map. `leftover_datasets` lists the datasets the attach left unreferenced (the raw upload when it was re-uploaded; the empty factory layer of a 'Culvert 01' created here), each {dataset_pk, name, reason}, with a `leftover_hint`; the tool deletes nothing — the user may delete them. The culvert engine conveys flow through each culvert in a run (GPU lanes and localhost; the multi-core CPU lanes refuse a culvert scenario). `outcome` is exactly one of: `attached` (row_id, gn_layer, dataset_pk, dataset_alternate — the WFS typename — and every row id seen); `timed_out` (still importing or still creating the culvert layer: call again with the same arguments, except pass `retry_execution_id` as execution_id when the result carries one); `upload_failed` (the execution record, incl. its log, is returned verbatim — fix the file and upload again); `no_default_row`; `no_dataset` (finished but no resource was recorded). The PATCH is refused with a 400 if the dataset is not owned by you. Refused, with no request made: kind `breakline` — no REST create path exists for it at HEAD (TASK-3040 AC6), so attaching one would only pretend. Also refused without a request: an execution_id that is not the UUID the upload returned. One GeoJSON per kind: all of a kind's features travel in that one file. A rainfall polygon names its gauge in its `data` property — create that gauge with create_time_series under the exact same name.

  Paramètres, retour & exemple (5)

  Paramètres

  • kind · string · requis
    Which input the uploaded layer is: boundary, friction, inflow, rainfall, building, mesh_region or culvert ('structure' is a deprecated alias of building). breakline is refused (see below).
  • project_id · integer · requis
    The project ID
  • execution_id · string · requis
    `execution_id` returned by your multipart POST to <origin>/api/v2/uploads/upload/
  • timeout_seconds · integer · optionnel
    How long this call keeps polling the upload before it returns `timed_out` (default 240, ceiling 280 — the prod /mcp/ proxy cuts a call at 300 s). 0 = one status read, no waiting.
  • poll_interval_seconds · number · optionnel
    Seconds between polls (default 5)

  Exemple d'appel

  {"name": "attach_input_layer", "arguments": {"kind": "texte", "project_id": 1, "execution_id": "texte"}}

  Exemple de retour

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

• build_scenario≈ 1155 tokens

  Build a scenario's package (mesh + inputs) after showing what it will cost, and poll until built. Order of operations, so the number is shown before anything is spent: 1. GET the scenario detail. A record with no `boundary`/`computed_status` keys is a non-member's read of a public project → refused: a build needs the EDITOR role. 2. Re-call checks on `latest_run` (a re-POST is NOT deduplicated after `built`/`complete` — it would dispatch a duplicate build): no run → proceed; run `created`/`building` → resume polling, no POST; run `built`/`queued`/`computing`/`processing`/`complete` with `latest_run_is_valid` not false → return that state, no POST unless rebuild=true; run `error`/`cancelled`, or `latest_run_is_valid` false (the scenario was edited since the build) → proceed. 3. Spend gates, each a refusal with `outcome: "refused"` and no POST: the scenario has no boundary or its boundary row has no features (the server would admit the build and fail it in make_package); the estimate is None (resolution is 0/unset); the estimate is above 100,000 triangles and confirm is not true — the refusal states the number; re-call with confirm=true to proceed. An estimate of 0 over a boundary WITH features is buildable and is reported, not refused. 4. POST /projects/<id>/scenarios/<pk>/build/. Every 4xx comes back verbatim as a normal result with `http_status`: 422 MESH_TOO_LARGE (`error_code`, `estimate`, `ceiling`, `detail` — the server's hard ceiling; coarsen `resolution` or shrink the boundary; no run was created), 409 COMPUTE_TARGET_UNAVAILABLE, 400/403/404. A 409 WITHOUT an error_code is the dedup body ({status, run_id, detail}: a build is already in flight) — the tool resumes polling that run. 5. On 202 poll the detail's `computed_status` (created → building → built | error), bounded by timeout_seconds. Returns a COMPACT state, never the whole detail: `outcome` (built, error, cancelled, complete/queued/computing/processing for a run past the build, timed_out, or refused), `computed_status`, `mesh_triangle_count_estimate`, `posted`, the POST's `build` body + `http_status` when one was made, and the latest run's `run_id`, `run_status`, `error_message`, `user_message`, `mesh_triangle_count`. `timed_out` is normal (make_package re-downloads the terrain from S3 every build; minutes): call again with the same arguments — step 2 resumes polling the same run, it never POSTs twice — or cancel_run(run_id) if the run is stuck in `created` with no worker. `error` is terminal: `error_message` says why (fix the inputs, then call again — an errored latest run is rebuilt). Units: `resolution` — on the SCENARIO and on every MeshRegion FEATURE — is a LENGTH in metres; ANUGA maximum_triangle_area = resolution²/2 (FloatField default 100, not nullable; 0 makes the estimate None), and the estimate prices both the same way (TASK-3186). The smallest value becomes the raster cell size. A MeshRegion feature must carry `resolution_units = m` (features drawn in the map are marked automatically); an unmarked one makes the build answer 422 MESH_REGION_UNITS_UNMARKED, naming the conversion an operator runs.

  Paramètres, retour & exemple (6)

  Paramètres

  • confirm · boolean · optionnel
    Required (true) when the estimate is above 100,000 triangles — the tool refuses first and tells you the number. Default false.
  • rebuild · boolean · optionnel
    true to dispatch a NEW build of a scenario whose latest run is already built/complete and still valid (default false: the tool returns that state instead of duplicating the build).
  • project_id · integer · requis
    The project ID
  • scenario_id · integer · requis
    The scenario ID from create_scenario
  • timeout_seconds · integer · optionnel
    How long this call keeps polling before it returns `timed_out` (default 240, ceiling 280 — the prod /mcp/ proxy cuts a call at 300 s). 0 = one status read, no waiting.
  • poll_interval_seconds · number · optionnel
    Seconds between polls (default 5)

  Exemple d'appel

  {"name": "build_scenario", "arguments": {"project_id": 1, "scenario_id": 1}}

  Exemple de retour

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

• cancel_run≈ 170 tokens

  Cancel an in-flight simulation run. Works on runs in built, queued, or computing status. Cleans up compute resources (terminates EC2 instance, Celery task, or Batch job). Returns 409 if the run is already in a terminal state (complete, cancelled, or error).

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · integer · requis
    The run ID to cancel

  Exemple d'appel

  {"name": "cancel_run", "arguments": {"run_id": 1}}

  Exemple de retour

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

• create_observation_layer≈ 492 tokens

  Create a flood observation layer in a project and wait for its map layer. A flood observation layer holds real flood evidence (Flood marks, Timed levels, Gauge records, Dry points) that every historic run is compared with (Compare with observations). It is project-level: it is never a scenario input. POSTs /projects/<id>/flood-observations/, then polls the layer until its GeoServer layer exists (`ready`), usually a few seconds; until then add_observations refuses. On `timed_out`, call list_observations later.

  Paramètres, retour & exemple (6)

  Paramètres

  • title · string · requis
    Layer title, e.g. 'August 1998 survey'
  • project_id · integer · requis
    The project ID
  • datum_offset_m · ? · optionnel
    Metres ADDED to every stage on the layer to bring it onto the terrain datum. Required for vertical_datum=local; null means 0 otherwise
  • vertical_datum · string · optionnel
    The datum the layer's stages are on: terrain (default, 'Same as terrain'), local ('Local datum (constant offset)', needs datum_offset_m), or the vertical datum the levels were surveyed on: an EPSG vertical CRS (e.g. 'EPSG:5703') or the datum's own name (at most 32 characters). Ask the user; never assume one from the country
  • timeout_seconds · integer · optionnel
    How long to wait for the map layer (clamped to 280)
  • poll_interval_seconds · number · optionnel
    Seconds between layer polls

  Exemple d'appel

  {"name": "create_observation_layer", "arguments": {"title": "texte", "project_id": 1}}

  Exemple de retour

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

• create_project≈ 248 tokens

  Create a new ANUGA project. Returns the project record including its id, base_map and ui_url. The caller's own account becomes the owner. `projection` is the projected CRS every scenario in the project is meshed and run in — pick the UTM zone covering the site. The project's map is created alongside it; `ui_url` opens it — give it to the user. Next step for a new project: presign_terrain_upload.

  Paramètres, retour & exemple (2)

  Paramètres

  • name · string · requis
    Project name
  • projection · string · requis
    Working CRS as an EPSG string, normally the UTM zone of the site, e.g. 'EPSG:32756' (WGS 84 / UTM 56S)

  Exemple d'appel

  {"name": "create_project", "arguments": {"name": "texte", "projection": "texte"}}

  Exemple de retour

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

• create_scenario≈ 1094 tokens

  Create a DRAFT scenario (no build, no run) and report its mesh-triangle estimate. POSTs /projects/<id>/scenarios/ with the write fields, then GETs the scenario detail — the create response carries NO estimate; the detail's `mesh_triangle_count_estimate` (+ `_breakdown`) does. Returns a compact record (the same fields get_scenario answers with): id, name, the FK ids as stored, resolution, duration, `computed_status` (`created` = no run yet), the estimate and its breakdown, the price (`compute_cost_estimate` in USD, `vcpu_hours_estimate`), `inflow_anchor_mismatch`, and http_status. Next step: build_scenario (which asks for confirm=true above 100,000 triangles). Nothing is meshed or queued here. Units: `resolution` — on the SCENARIO and on every MeshRegion FEATURE — is a LENGTH in metres; ANUGA maximum_triangle_area = resolution²/2 (FloatField default 100, not nullable; 0 makes the estimate None), and the estimate prices both the same way (TASK-3186). The smallest value becomes the raster cell size. A MeshRegion feature must carry `resolution_units = m` (features drawn in the map are marked automatically); an unmarked one makes the build answer 422 MESH_REGION_UNITS_UNMARKED, naming the conversion an operator runs. The server does NOT validate that the FK ids belong to `project_id` — pass the row ids attach_input_layer / get_terrain returned for THIS project. Every FK is nullable at create time, and the build fails later on a scenario with no terrain, or with neither an inflow nor a rainfall. A `boundary` whose row has no features (the default 'Boundary 01' before attach_input_layer) is accepted here and refused by build_scenario. The estimate is None when resolution is 0; an estimate of 0 with a real boundary is a very coarse mesh, not an error.

  Paramètres, retour & exemple (14)

  Paramètres

  • name · string · requis
    Scenario name
  • inflow · ? · optionnel
    Inflow row id (optional; the build needs an inflow OR a rainfall)
  • culvert · ? · optionnel
    Culvert row id (optional; attach_input_layer kind=culvert → row_id). The build refuses a culvert missing its shape, size or invert levels.
  • terrain · ? · optionnel
    Terrain id (get_terrain → terrain.id); the build fails without one
  • boundary · ? · optionnel
    Boundary row id (attach_input_layer kind=boundary → row_id)
  • building · ? · optionnel
    Building row id (optional)
  • duration · integer · requis
    Simulation duration in seconds (e.g. 43200 = 12 h)
  • friction · ? · optionnel
    Friction row id (optional)
  • rainfall · ? · optionnel
    Rainfall row id (optional; the build needs an inflow OR a rainfall)
  • structure · ? · optionnel
    Deprecated alias of `building` (TASK-3586); ignored when `building` is given.
  • project_id · integer · requis
    The project ID
  • resolution · number · requis
    Mesh resolution as a LENGTH in metres (ANUGA maximum_triangle_area = resolution²/2). Coarser (larger) = fewer triangles: on a ~13 km² boundary 36-40 m gives ~16-20k triangles, 10 m ~255k, 1 m ~25M (refused by the API).
  • description · string · optionnel
    Free-text description (optional)
  • mesh_region · ? · optionnel
    MeshRegion row id (optional): finer meshing inside its polygons, each feature's `resolution` a LENGTH in metres (see the units note).

  Exemple d'appel

  {"name": "create_scenario", "arguments": {"name": "texte", "duration": 1, "project_id": 1, "resolution": 1}}

  Exemple de retour

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

• create_time_series≈ 638 tokens

  Create a time series (rain gauge, hydrograph, tide/stage) in a project. POSTs /projects/<id>/time-series/ with `series_type` and `units` as top-level fields. `series_type` is checked against the four choices and `data` against the {"rowData": [{timestamp, value}, ...]} shape before any request is made — the API answers 500 (not 400) to a malformed row. Returns a compact record — id, name, series_type, units, timezone, row_count, http_status — not the echoed rows; fetch the full row with the REST API (GET /projects/<id>/time-series/<id>/) if you need to round-trip it. A rainfall polygon references its gauge by the series NAME, so create the gauges with the exact names the rainfall GeoJSON's features carry.

  Paramètres, retour & exemple (9)

  Paramètres

  • data · object · requis
    The rows: {"rowData": [{"timestamp": "1998-08-17T00:00:00", "value": 1.5}, ...]}. Timestamps ISO 8601 (a trailing Z is tolerated), values numeric. Validated here before anything is sent.
  • name · string · requis
    Series name, kept VERBATIM — a rainfall polygon binds to its gauge by this exact name (its `data` property), so use the name the GeoJSON features carry
  • units · string · optionnel
    Display label for the values, e.g. 'mm/hr', 'm^3/s', 'm' (optional)
  • source · string · optionnel
    Where the data came from, e.g. a gauge id or agency (optional)
  • timezone · string · optionnel
    IANA timezone of the timestamps (default 'UTC'), e.g. 'Australia/Sydney'
  • project_id · integer · requis
    The project ID
  • description · string · optionnel
    Free-text description (optional)
  • series_type · string · optionnel
    One of hyetograph (rainfall depth/intensity — the default), hydrograph (flow, read by the Hydrographs panel and inflow boundaries), stage (water level, e.g. a tide) or generic. Sent as a top-level field.
  • location_name · string · optionnel
    Human-readable location of the gauge (optional)

  Exemple d'appel

  {"name": "create_time_series", "arguments": {"data": {}, "name": "texte", "project_id": 1}}

  Exemple de retour

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

• delete_observation≈ 205 tokens

  Delete one flood observation and its photos (cannot be undone). DELETEs /projects/<id>/flood-observations/<layer>/observations/<fid>/; a missing fid is an error (404), not a silent success.

  Paramètres, retour & exemple (3)

  Paramètres

  • fid · integer · requis
    The observation's fid
  • layer_id · integer · requis
    The flood observation layer id
  • project_id · integer · requis
    The project ID

  Exemple d'appel

  {"name": "delete_observation", "arguments": {"fid": 1, "layer_id": 1, "project_id": 1}}

  Exemple de retour

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

• finalize_terrain_upload≈ 378 tokens

  Step 2 of a terrain import: register the PUT GeoTIFF as a Terrain and start the import. Call this only after the presigned PUT returned 200. Creates the Terrain row (status `creating`) and queues the import chain — reproject to UTM, publish the layer + hillshade, style — which also seeds the project's six default boundary, friction, inflow, rainfall, building and mesh-region rows. Returns 202 with the terrain record; keep its `id` for get_terrain. A 400 UPLOAD_NOT_FOUND means no object is at `staging_key`: the PUT did not land (check its status code and Content-Type) — do not retry finalize until it has.

  Paramètres, retour & exemple (4)

  Paramètres

  • title · string · optionnel
    Terrain title (default: the filename without .tif)
  • process_id · string · optionnel
    `process_id` returned by presign_terrain_upload (pass it so the upload's progress record is reused; the API tolerates its absence)
  • project_id · integer · requis
    The project ID
  • staging_key · string · requis
    `staging_key` returned by presign_terrain_upload

  Exemple d'appel

  {"name": "finalize_terrain_upload", "arguments": {"project_id": 1, "staging_key": "texte"}}

  Exemple de retour

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

• get_observation_comparison≈ 681 tokens

  Compare a run with the project's flood observations: how well does it match them? Returns `headline` (the figures to tell the user, e.g. "47 observations · 31 within ±0.30 m (66%) · bias -0.12 m · RMSE 0.35 m · 1 excluded"), `headline_numbers` (the same as numbers), `tolerance_m` (used) and `default_tolerance_m` (the project's saved one), `statistics` (the API's summary: n, within, within_pct, bias_m, rmse_m, weighted_rmse_m, mae_m, max_abs_m, excluded, not_scored by reason, gauges), `gauges` (Gauge records: peak error, timing error, NSE), `datum_checks` (warn the user only when `warning` is true: both datums known and different; `not_recorded` = the terrain has no recorded datum, stated in `note`, not a warning) and one row per observation: observed_m / modelled_m / residual_m (modelled - observed, + = model high), within, scored / not_scored_reason, match (`outside_run_window` = not this flood), excluded + exclusion {reason, by, at}. `sampling` counts how the modelled values were read: `centroid` (the peak of the mesh triangle the observation sits in), `nearest_node_fallback` (an older run without that peak: the nearest mesh node's value, tell the user) and `nearest_node` (just outside the mesh); each row's `sample.method` says which. There is no pass or fail: report the figures. A run that is not historic has none (`has_comparison` false) — do not retry it.

  Paramètres, retour & exemple (5)

  Paramètres

  • fid · ? · optionnel
    With layer_id: the observation's fid (list_observations)
  • run_id · integer · requis
    The run ID (a historic run; others are not compared with observations)
  • layer_id · ? · optionnel
    With fid: narrow the rows to ONE flood observation and add its history
  • tolerance · ? · optionnel
    Metres within which a residual counts as within (default: the project's saved tolerance, 0.3 unless an Editor changed it; presets 0.15, 0.3, 0.4; above 0 and at most 5). Not stored: it only changes this answer
  • include_series · boolean · optionnel
    Keep each Gauge record's modelled stage series (every saved frame); default false

  Exemple d'appel

  {"name": "get_observation_comparison", "arguments": {"run_id": 1}}

  Exemple de retour

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

• get_project≈ 235 tokens

  Get one ANUGA project: id, name, projection, visibility, your role, its base map — and the link to it. Returns the project record (`id`, `name`, `projection` (EPSG code), `simple_view_config`, `visibility`, `owner_username`, `my_role`, `base_map`) plus `ui_url`: the link that opens the project's map, for the user (`<site>/catalogue/#/map/<base_map>`; null while a new project's map is still being created). Scenarios are NOT listed here — use get_scenario with a scenario id.

  Paramètres, retour & exemple (1)

  Paramètres

  • project_id · integer · requis
    The project ID

  Exemple d'appel

  {"name": "get_project", "arguments": {"project_id": 1}}

  Exemple de retour

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

• get_run≈ 242 tokens

  Get full details of a simulation run including timing and results. Returns the complete run record: status, progress, timing (start/end timestamps, duration), compute details (backend, instance type, cost), mesh info, error messages, and result log. Use get_run_status for lightweight polling; use this for final results. The presigned `s3_*_url` download links are ELIDED — each is a 6-hour capability and no tool relays one. The results stay viewable through the `gn_layer_*` entries (published WMS layers on the project's map).

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · integer · requis
    The run ID

  Exemple d'appel

  {"name": "get_run", "arguments": {"run_id": 1}}

  Exemple de retour

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

• get_run_status≈ 233 tokens

  Lightweight status check for a simulation run (fast, <50ms). Use this for polling instead of get_run. Returns only: id, status, `phase`, progress_pct (0-100), eta_seconds, error_message, and compute_backend. `phase` is never empty: it is `status`, except `preparing_inputs` while a `computing` run has no progress yet (it is downloading its input package and building the domain — minutes on a big model; this is NOT a stall). Poll every 5-10 seconds. Terminal states: complete, error, cancelled.

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · integer · requis
    The run ID

  Exemple d'appel

  {"name": "get_run_status", "arguments": {"run_id": 1}}

  Exemple de retour

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

• get_scenario≈ 557 tokens

  Get a scenario's COMPACT state: its `computed_status`, inputs, estimate and price. Returns a compact record, never the raw ~50 KB detail: `scenario_id`, `computed_status`, `mesh_triangle_count_estimate` and its `_breakdown`, `latest_run_is_valid`, the latest run's `run_id`, `run_status`, `error_message`, `user_message`, `status_detail` and `mesh_triangle_count` — plus what the scenario IS and what it will cost: `name`, `description`, `project`, `resolution`, `duration`, the input row ids (`terrain`, `boundary`, `friction`, `inflow`, `rainfall`, `building`, `mesh_region`, `culvert`), `compute_cost_estimate` (USD), `vcpu_hours_estimate`, and `inflow_anchor_mismatch` (null unless an inflow series starts after the model does, whose first value is then held backwards). The `computed_status` field (there is NO `status` key on a scenario) is derived from the latest run and will be one of: created, building, built, queued, computing, processing, complete, error, or cancelled — `created` also means no run exists yet. A scenario must be `built` before it can be run. `latest_run_is_valid` is false after any edit since the last build. A non-member reading a public project's scenario gets a reduced record: the fields the server withholds (the input ids, the price, `inflow_anchor_mismatch`) are ABSENT here rather than reported as null — "withheld" is not "no terrain, no cost" — while the run-state keys, `computed_status` among them, read null. No presigned S3 URL is returned by any read tool (each is a 6-hour capability): results stay viewable through a run's `gn_layer_*` WMS entries — use get_run for the full run record.

  Paramètres, retour & exemple (2)

  Paramètres

  • project_id · integer · requis
    The project ID
  • scenario_id · integer · requis
    The scenario ID

  Exemple d'appel

  {"name": "get_scenario", "arguments": {"project_id": 1, "scenario_id": 1}}

  Exemple de retour

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

• get_terrain≈ 574 tokens

  Poll a terrain's import until it is `ready` (or `error`), bounded by timeout_seconds. Returns `outcome` — exactly one of `ready`, `error`, `timed_out`, `not_found` (the project has no terrain yet; an unknown terrain_id is an API 404 error instead) — plus the last `status` seen (creating → styling → ready | error) and `phase` (that status, or `not_found`; never empty), `polls`, `elapsed_seconds` and the full `terrain` record (its `gn_layer` is the published elevation dataset pk once ready). An import takes minutes to tens of minutes (the SAME 32 MB 1 m DEM measured 4.5 min once and 26 min once — the worker's S3 download speed dominates), so `timed_out` is normal and NOT a failure: keep calling with the same arguments while `status` is still `creating`/`styling`; several calls in a row is expected. `error` is terminal — the import failed and no default input rows were seeded; upload a corrected GeoTIFF as a new terrain. `ready` is written by the import task; the project's default input rows (Boundary 01, Friction 01, Inflow 01, Rainfall 01, Building 01, MeshRegion 01, one GeoNode layer each) are seeded by the NEXT task in the chain and appear over the following ~30 s. Poll the input-layer list until it is non-empty before attaching your own layer to a default row.

  Paramètres, retour & exemple (4)

  Paramètres

  • project_id · integer · requis
    The project ID
  • terrain_id · ? · optionnel
    The terrain ID from finalize_terrain_upload. Omit to follow the project's newest terrain.
  • timeout_seconds · integer · optionnel
    How long this call keeps polling before it returns `timed_out` (default 240, ceiling 280 — the prod /mcp/ proxy cuts a call at 300 s). 0 = one status read, no waiting.
  • poll_interval_seconds · number · optionnel
    Seconds between polls (default 5)

  Exemple d'appel

  {"name": "get_terrain", "arguments": {"project_id": 1}}

  Exemple de retour

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

• list_inputs≈ 300 tokens

  List every input layer row of a project, per kind, with whether it has features. For each of boundary, friction, inflow, rainfall, building, mesh_region and culvert: the rows (`row_id`, `title`, `gn_layer` — the dataset pk — and `dataset_alternate`, the `workspace:name` WFS typename) and `has_features`. `has_features` comes from the API for boundary, rainfall, mesh_region and culvert; for friction, inflow and building (whose records do not carry it) it is a WFS feature count, at most 24 lookups per call — past that, or when a lookup fails, it is null (unknown, not false). A row with no `gn_layer` has no layer yet (`has_features` false). Use the row ids with create_scenario; this is the listing primitive — no need to probe files.

  Paramètres, retour & exemple (1)

  Paramètres

  • project_id · integer · requis
    The project ID

  Exemple d'appel

  {"name": "list_inputs", "arguments": {"project_id": 1}}

  Exemple de retour

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

• list_observations≈ 305 tokens

  List a project's flood observation layers, or one layer's observations. Without layer_id: every layer (layer_id, title, dataset_alternate, vertical_datum, datum_offset_m, has_features). With layer_id: {layer, count, results} where each observation carries its `fid` (the key for update_observation / delete_observation), subtype + subtype_label, stage/depth, sigma, bound, the observed window in UTC, `datum` status (an `unknown` datum is not scored), `photo_count` and `problems` (fields drawn in the map that fail validation, reported, never fixed).

  Paramètres, retour & exemple (2)

  Paramètres

  • layer_id · ? · optionnel
    A flood observation layer id; omit to list the project's layers instead
  • project_id · integer · requis
    The project ID

  Exemple d'appel

  {"name": "list_observations", "arguments": {"project_id": 1}}

  Exemple de retour

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

• list_projects≈ 171 tokens

  List ANUGA simulation projects accessible to the authenticated user. Returns a paginated list of projects with their names, projections, and base map references.

  Paramètres, retour & exemple (2)

  Paramètres

  • page · integer · optionnel
    Page number (default 1)
  • page_size · integer · optionnel
    Results per page, max 100 (default 100)

  Exemple d'appel

  {"name": "list_projects", "arguments": {"page": 1, "page_size": 1}}

  Exemple de retour

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

• list_runs≈ 274 tokens

  List all simulation runs across all scenarios in a project. Returns a paginated list of runs. Optionally filter by status to find active, completed, or failed runs. Each row's presigned `s3_*_url` download links are elided (6-hour capabilities).

  Paramètres, retour & exemple (4)

  Paramètres

  • page · integer · optionnel
    Page number (default 1)
  • page_size · integer · optionnel
    Results per page, max 100 (default 100)
  • project_id · integer · requis
    The project ID
  • status_filter · ? · optionnel
    Filter by status: created, building, built, queued, computing, processing, complete, error, cancelled. Omit for all.

  Exemple d'appel

  {"name": "list_runs", "arguments": {"project_id": 1}}

  Exemple de retour

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

• list_time_series≈ 222 tokens

  List a project's time series (rain gauges, hydrographs, tides) — never their rows. Each series: `id`, `name` (a rainfall polygon binds to its gauge by this exact name), `series_type`, `units`, `timezone`, `row_count`, `first_timestamp` and `last_timestamp`. The data rows themselves are dropped (a project's list is megabytes); fetch one series with the REST API (GET /projects/<id>/time-series/<id>/) if you need its values.

  Paramètres, retour & exemple (1)

  Paramètres

  • project_id · integer · requis
    The project ID

  Exemple d'appel

  {"name": "list_time_series", "arguments": {"project_id": 1}}

  Exemple de retour

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

• presign_terrain_upload≈ 550 tokens

  Step 1 of a terrain import: get a presigned S3 PUT URL for a GeoTIFF DEM. The agent moves the bytes itself — no tool accepts file contents. After this call, PUT the file straight to `upload_url`, sending the SAME Content-Type you passed here (it is part of the signature; a mismatch is a 403 SignatureDoesNotMatch before it is anything else): curl -sS -X PUT -H "Content-Type: image/tiff" --upload-file /path/dem.tif "$UPLOAD_URL" then call finalize_terrain_upload with the returned staging_key and process_id. Nothing exists in Hydrata until finalize; the URL expires after `expires_in` seconds (3600). Platform guidance: keep the terrain extent within 5° across and 40,000 km² (200 × 200 km). The API enforces that cap on its bbox-fetch path; an uploaded GeoTIFF is only rejected above 5 GiB, but a larger DEM will not mesh or run well. The GeoTIFF must carry a CRS; the import reprojects it to the site's UTM zone and builds a hillshade. Fallback when a presigned PUT is impossible: multipart-POST the file with the same credential to /api/v2/anuga/projects/<id>/terrain/upload/ (form field `file`, optional `title`), which creates the terrain in one step — then get_terrain.

  Paramètres, retour & exemple (4)

  Paramètres

  • size · ? · optionnel
    File size in bytes (`stat -c %s <file>`). The API rejects > 5 GiB up front. Omit if unknown.
  • filename · string · requis
    Base name of the GeoTIFF, e.g. 'dem.tif' (a name only — never contents)
  • project_id · integer · requis
    The project ID
  • content_type · string · optionnel
    MIME type the PUT will send (default 'image/tiff'). It is SIGNED into the URL, so the PUT must send exactly this Content-Type header.

  Exemple d'appel

  {"name": "presign_terrain_upload", "arguments": {"filename": "texte", "project_id": 1}}

  Exemple de retour

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

• retry_run≈ 160 tokens

  Retry a failed simulation run. Resets an errored run back to 'created' status and triggers a new package build. The same run ID is reused. Only valid when status is 'error'. Returns 409 for any other state.

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · integer · requis
    The run ID to retry

  Exemple d'appel

  {"name": "retry_run", "arguments": {"run_id": 1}}

  Exemple de retour

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

• set_comparison_tolerance≈ 261 tokens

  Save a project's default tolerance for comparing runs with flood observations. Needs Editor (or above). Every later get_observation_comparison (and the map's Compare with observations tab) uses it unless a tolerance is passed. Only save it when the user asks to change the project's default; to show the figures at another tolerance, pass `tolerance` to get_observation_comparison.

  Paramètres, retour & exemple (2)

  Paramètres

  • project_id · integer · requis
    The project ID
  • tolerance_m · number · requis
    The project's default tolerance in metres (above 0 and at most 5; presets 0.15, 0.3, 0.4)

  Exemple d'appel

  {"name": "set_comparison_tolerance", "arguments": {"project_id": 1, "tolerance_m": 1}}

  Exemple de retour

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

• set_observation_exclusion≈ 370 tokens

  Exclude a flood observation from ONE run's comparison with observations, or include it again. Needs Editor (or above) on the project. The exclusion is logged with the user and reason (nothing is overwritten) and keyed on (run, layer, fid), so it survives a recompute. The figures change at once: `headline_after` is the run's headline with the change applied. To exclude, the user must give the reason: if they have not, ASK them; do not make one up.

  Paramètres, retour & exemple (5)

  Paramètres

  • fid · integer · requis
    The observation's fid
  • reason · string · optionnel
    WHY the engineer excludes it, in their words (required to exclude; never invent one — ask the user). Optional when including it again
  • run_id · integer · requis
    The run ID (a historic run)
  • excluded · boolean · optionnel
    true to exclude (default), false to include it again
  • layer_id · integer · requis
    The flood observation layer id

  Exemple d'appel

  {"name": "set_observation_exclusion", "arguments": {"fid": 1, "run_id": 1, "layer_id": 1}}

  Exemple de retour

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

• start_simulation≈ 274 tokens

  Start a flood simulation run for a built scenario. The scenario must be in 'built' status. Returns 202 with the new run. The run transitions through: built → queued → computing → processing → complete. After starting, poll get_run_status to track progress. Returns 409 if the scenario is not in the correct state. The returned run record has its presigned `s3_*_url` links elided (6-hour capabilities).

  Paramètres, retour & exemple (2)

  Paramètres

  • scenario_id · integer · requis
    The scenario ID to run
  • compute_backend · string · optionnel
    Compute backend: 'local' (Celery), 'ec2' (dedicated instance), or 'batch' (AWS Batch spot, cheapest). Default: 'local'

  Exemple d'appel

  {"name": "start_simulation", "arguments": {"scenario_id": 1}}

  Exemple de retour

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

• update_observation≈ 316 tokens

  Edit one flood observation (PATCH; only the fields given change). The API checks the stored observation merged with `changes` and refuses (400, every bad field named) rather than store a half-valid one. Photos are not fields: attach a link with add_observation_photo_link.

  Paramètres, retour & exemple (4)

  Paramètres

  • fid · integer · requis
    The observation's fid (from list_observations / add_observations)
  • changes · object · requis
    Only the fields to change, in the add_observations write shape (e.g. {"stage_m": 2.5} or a new geometry); validated by the API against the stored observation (a flood_mark or dry_point must keep a date window or a flood_name)
  • layer_id · integer · requis
    The flood observation layer id
  • project_id · integer · requis
    The project ID

  Exemple d'appel

  {"name": "update_observation", "arguments": {"fid": 1, "changes": {}, "layer_id": 1, "project_id": 1}}

  Exemple de retour

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

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://hydrata.com/mcp/