Hydrata - ANUGA Flood Simulation

{
  "id": "aix_777d4c307e",
  "name": "Hydrata - ANUGA Flood Simulation",
  "operator": "(unclaimed - source: registry-official · publisher: com.hydrata)",
  "description": "Run ANUGA flood simulations, track progress, and retrieve results on Hydrata Cloud.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-11-09",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "api-integration",
    "browser-automation"
  ],
  "protocols": {
    "mcp": "https://hydrata.com/mcp/",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 3375,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 41,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-11-09T13:00:55.625Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "repository",
      "url": "https://github.com/Hydrata/hydrata-mcp-server"
    }
  ],
  "avatar": "https://github.com/Hydrata.png?size=160",
  "socials": [
    {
      "label": "github",
      "url": "https://github.com/Hydrata"
    }
  ],
  "profile": {
    "mcp_server": "Hydrata",
    "mcp_version": "4.0.5",
    "tool_count": 28,
    "tools": [
      {
        "name": "list_projects",
        "description": "List ANUGA simulation projects accessible to the authenticated user.\n\nReturns a paginated list of projects with their names, projections,\nand base map references."
      },
      {
        "name": "get_project",
        "description": "Get one ANUGA project: id, name, projection, visibility, your role, its base map — and the link to it.\n\nReturns the project record (`id`, `name`, `projection` (EPSG code),\n`simple_view_config`, `visibility`, `owner_username`, `my_role`,\n`base_map`) plus `ui_url`: the link that opens the project's map, for the\nuser (`<site>/catalogue/#/map/<base_map>`; null while a new project's map\nis still being created). Scenarios are NOT listed here — use get_scenario\nwith a scenario id."
      },
      {
        "name": "get_scenario",
        "description": "Get a scenario's COMPACT state: its `computed_status`, inputs, estimate and price.\n\nReturns a compact record, never the raw ~50 KB detail: `scenario_id`,\n`computed_status`, `mesh_triangle_count_estimate` and its `_breakdown`,\n`latest_run_is_valid`, the latest run's `run_id`, `run_status`,\n`error_message`, `user_message`, `status_detail` and `mesh_triangle_count`\n— plus what the scenario IS and what it will cost: `name`, `description`,\n`project`, `resolution`, `duration`, the input row ids (`terrain`,\n`boundary`, `friction`, `inflow`, `rainfall`, `building`, `mesh_region`, `culvert`),\n`compute_"
      },
      {
        "name": "start_simulation",
        "description": "Start a flood simulation run for a built scenario.\n\nNeeds a launch-level agent key (a run spends compute); a read or draft key\ngets 403 AGENT_LEVEL_INSUFFICIENT — the user creates a launch key on the\nsite's Agent keys page (/agents/).\n\nThe scenario must be in 'built' status. Returns 202 with the new run.\nThe run transitions through: built → queued → computing → processing → complete.\n\nAfter starting, poll get_run_status to track progress. Returns 409\nif the scenario is not in the correct state. The returned run record has\nits presigned `s3_*_url` links elided (6-hour capabilities).\n\nINPUT REVI"
      },
      {
        "name": "get_run_status",
        "description": "Lightweight status check for a simulation run (fast, <50ms).\n\nUse this for polling instead of get_run. Returns only: id, status,\n`phase`, progress_pct (0-100), eta_seconds, error_message, and\ncompute_backend.\n\n`phase` is never empty: it is `status`, except `preparing_inputs` while a\n`computing` run has no progress yet (it is downloading its input package\nand building the domain — minutes on a big model; this is NOT a stall).\nPoll every 5-10 seconds. Terminal states: complete, error, cancelled."
      },
      {
        "name": "get_run",
        "description": "Get full details of a simulation run including timing and results.\n\nReturns the complete run record: status, progress, timing (start/end\ntimestamps, duration), compute details (backend, instance type, cost),\nmesh info, error messages, and result log. Use get_run_status for\nlightweight polling; use this for final results.\n\nThe presigned `s3_*_url` download links are ELIDED — each is a 6-hour\ncapability and no tool relays one. The results stay viewable through the\n`gn_layer_*` entries (published WMS layers on the project's map)."
      },
      {
        "name": "cancel_run",
        "description": "Cancel an in-flight simulation run.\n\nNeeds a launch-level agent key; a read or draft key gets 403\nAGENT_LEVEL_INSUFFICIENT.\n\nWorks on runs in built, queued, or computing status. Cleans up\ncompute resources (terminates EC2 instance, Celery task, or Batch job).\n\nReturns 409 if the run is already in a terminal state\n(complete, cancelled, or error)."
      },
      {
        "name": "retry_run",
        "description": "Retry a failed simulation run.\n\nNeeds a launch-level agent key (a retry rebuilds the package and can start\nAWS Batch); a read or draft key gets 403 AGENT_LEVEL_INSUFFICIENT.\n\nStarts a fresh package build of the run's scenario as a NEW run, which\nbecomes the scenario's latest run. The errored run keeps its status and\nerror as history, and the response describes that old run; the new run's\nID is get_scenario's `run_id`. Only valid when status is 'error'. Returns\n409 for any other state."
      },
      {
        "name": "list_runs",
        "description": "List all simulation runs across all scenarios in a project.\n\nReturns a paginated list of runs. Optionally filter by status\nto find active, completed, or failed runs. Each row's presigned\n`s3_*_url` download links are elided (6-hour capabilities)."
      },
      {
        "name": "create_project",
        "description": "Create a new ANUGA project. Returns the project record including its id, base_map and ui_url.\n\nThe caller's own account becomes the owner. `projection` is the projected\nCRS every scenario in the project is meshed and run in — pick the UTM zone\ncovering the site. The project's map is created alongside it; `ui_url`\nopens it — give it to the user. A project you create is unpublished\n(`is_published: false`): only its owner and members can see it until the\nuser presses Publish in its Sharing panel in the browser — you cannot\npublish it. Next step for a new project: presign_terrain_upload."
      },
      {
        "name": "presign_terrain_upload",
        "description": "Step 1 of a terrain import: get a presigned S3 PUT URL for a GeoTIFF DEM.\n\nThe import needs a launch-level agent key: a draft key can presign, but\nfinalize_terrain_upload (and the multipart fallback below) answer a read or\ndraft key 403 AGENT_LEVEL_INSUFFICIENT — check the key before moving bytes.\n\nThe agent moves the bytes itself — no tool accepts file contents. After this\ncall, PUT the file straight to `upload_url`, sending the SAME Content-Type\nyou passed here (it is part of the signature; a mismatch is a 403\nSignatureDoesNotMatch before it is anything else):\n\n    curl -sS -X PUT -H \"Conten"
      },
      {
        "name": "finalize_terrain_upload",
        "description": "Step 2 of a terrain import: register the PUT GeoTIFF as a Terrain and start the import.\n\nNeeds a launch-level agent key (the import can start AWS Batch); a read or\ndraft key gets 403 AGENT_LEVEL_INSUFFICIENT — the user creates a launch key\non the site's Agent keys page (/agents/).\n\nCall this only after the presigned PUT returned 200. Creates the Terrain row\n(status `creating`) and queues the import chain — reproject to UTM, publish\nthe layer + hillshade, style — which also seeds the project's six default\nboundary, friction, inflow, rainfall, building and mesh-region rows.\nReturns 202 with the "
      },
      {
        "name": "get_terrain",
        "description": "Poll a terrain's import until it is `ready` (or `error`), bounded by timeout_seconds.\n\nReturns `outcome` — exactly one of `ready`, `error`, `timed_out`, `not_found`\n(the project has no terrain yet; an unknown terrain_id is an API 404 error\ninstead) — plus the last `status` seen (creating → styling → ready | error)\nand `phase` (that status, or `not_found`; never empty),\n`polls`, `elapsed_seconds` and the full `terrain` record (its `gn_layer` is\nthe published elevation dataset pk once ready). An import takes minutes to\ntens of minutes (the SAME 32 MB 1 m DEM measured 4.5 min once and 26 min\nonce"
      },
      {
        "name": "create_time_series",
        "description": "Create a time series (rain gauge, hydrograph, tide/stage) in a project.\n\nPOSTs /projects/<id>/time-series/ with `series_type` and `units` as\ntop-level fields. `series_type` is checked against the four choices and\n`data` against the {\"rowData\": [{timestamp, value}, ...]} shape before any\nrequest is made — the API answers 500 (not 400) to a malformed row.\nReturns a compact record — id, name, series_type, units, timezone,\nrow_count, http_status — not the echoed rows; fetch the full row with the\nREST API (GET /projects/<id>/time-series/<id>/) if you need to round-trip it.\nA rainfall polygon refere"
      },
      {
        "name": "attach_input_layer",
        "description": "Attach a GeoJSON you uploaded to GeoNode as the project's boundary, friction, inflow, rainfall, building, mesh_region or culvert layer.\n\nThe agent moves the bytes: first upload the GeoJSON yourself, with the\nsame agent key, to GeoNode's upload endpoint at the site origin:\n\n    curl -sS -H 'Authorization: Bearer hk_...' -F \"base_file=@/path/rainfall.geojson\" https://<site>/api/v2/uploads/upload/\n\n→ JSON with `execution_id`. Then call this tool with it. The tool polls\nGET /api/v2/resource-service/execution-status/<execution_id> (bounded by\ntimeout_seconds; statuses ready → running → finished | f"
      },
      {
        "name": "list_inputs",
        "description": "List every input layer row of a project, per kind, with whether it has features.\n\nFor each of boundary, friction, inflow, rainfall, building, mesh_region and culvert:\nthe rows (`row_id`, `title`, `gn_layer` — the dataset pk — and\n`dataset_alternate`, the `workspace:name` WFS typename) and `has_features`.\n`has_features` is the API's own answer for every kind. It is null only when\na row's record does not carry it: treat null as unknown, not as empty. A row\nwith no `gn_layer` has no layer yet (`has_features` false). Use the row ids with\ncreate_scenario; this is the listing primitive — no need to "
      },
      {
        "name": "list_time_series",
        "description": "List a project's time series (rain gauges, hydrographs, tides) — never their rows.\n\nEach series: `id`, `name` (a rainfall polygon binds to its gauge by this\nexact name), `series_type`, `units`, `timezone`, `row_count`,\n`first_timestamp` and `last_timestamp`. The data rows themselves are\ndropped (a project's list is megabytes); fetch one series with the REST API\n(GET /projects/<id>/time-series/<id>/) if you need its values."
      },
      {
        "name": "create_observation_layer",
        "description": "Create a flood observation layer in a project and wait for its map layer.\n\nA flood observation layer holds real flood evidence (Flood marks, Timed\nlevels, Gauge records, Dry points) that every historic run is compared\nwith (Compare with observations). It is project-level: it is never a scenario input.\nPOSTs /projects/<id>/flood-observations/, then polls the layer until its\nGeoServer layer exists (`ready`), usually a few seconds; until then\nadd_observations refuses. On `timed_out`, call list_observations later."
      },
      {
        "name": "list_observations",
        "description": "List a project's flood observation layers, or one layer's observations.\n\nWithout layer_id: every layer (layer_id, title, dataset_alternate, vertical_datum,\ndatum_offset_m, has_features). With layer_id: {layer, count, results} where each\nobservation carries its `fid` (the key for update_observation / delete_observation),\nsubtype + subtype_label, stage/depth, sigma, bound, the observed window in UTC,\n`datum` status (an `unknown` datum is not scored), `photo_count` and `problems`\n(fields drawn in the map that fail validation, reported, never fixed)."
      },
      {
        "name": "add_observations",
        "description": "Add flood observations (Flood mark, Timed level, Gauge record, Dry point) to a layer.\n\nPOSTs each observation to /projects/<id>/flood-observations/<layer>/observations/\nin order. The API validates every field: a row it refuses (400) is listed in\n`rejected` with its `problems` and the rest still land; a refusal that is not\nabout the row (403 not an Editor, 404, 409) stops the batch and is reported in\n`stopped`, with `not_sent_count`. Stages are on the LAYER's vertical datum.\nPhotos are not part of an observation: attach a link with add_observation_photo_link."
      },
      {
        "name": "update_observation",
        "description": "Edit one flood observation (PATCH; only the fields given change).\n\nThe API checks the stored observation merged with `changes` and refuses\n(400, every bad field named) rather than store a half-valid one. Photos are\nnot fields: attach a link with add_observation_photo_link."
      },
      {
        "name": "delete_observation",
        "description": "Delete one flood observation and its photos (cannot be undone).\n\nDELETEs /projects/<id>/flood-observations/<layer>/observations/<fid>/; a\nmissing fid is an error (404), not a silent success."
      },
      {
        "name": "add_observation_photo_link",
        "description": "Attach a photo to a flood observation as a reference LINK (never a file).\n\nMCP never uploads photo bytes. A local path, file:// URL or data: URI is\nrefused: to upload a photo file, open the observation in the map and use the\nphoto strip on its form (JPEG, PNG or HEIC, 25 MB, 10 per observation).\nThe link counts toward the 10."
      },
      {
        "name": "get_observation_comparison",
        "description": "Compare a run with the project's flood observations: how well does it match them?\n\nReturns `headline` (the figures to tell the user, e.g. \"47 observations · 31\nwithin ±0.30 m (66%) · bias -0.12 m · RMSE 0.35 m · 1 excluded\"),\n`headline_numbers` (the same as numbers), `tolerance_m` (used) and\n`default_tolerance_m` (the project's saved one), `statistics`\n(the API's summary: n, within, within_pct, bias_m, rmse_m, weighted_rmse_m, mae_m, max_abs_m,\nexcluded, not_scored by reason, gauges), `gauges` (Gauge records: peak error,\ntiming error, NSE), `datum_checks` (warn the user only when `warning` is "
      },
      {
        "name": "set_observation_exclusion",
        "description": "Exclude a flood observation from ONE run's comparison with observations, or include it again.\n\nNeeds Editor (or above) on the project. The exclusion is logged with the user\nand reason (nothing is overwritten) and keyed on (run, layer, fid), so it\nsurvives a recompute. The figures change at once: `headline_after` is the\nrun's headline with the change applied. To exclude, the user must give the\nreason: if they have not, ASK them; do not make one up."
      }
    ],
    "profiled_at": "2026-10-22T03:00:55.265Z"
  },
  "unreachable": false
}