MCP-Server
Hydrata - ANUGA Flood Simulation
com.hydrata/hydrata-mcp-server
Was dieses MCP kann
Creates and manages ANUGA flood simulation projects, imports terrain and geospatial inputs, builds scenarios, runs simulations, and retrieves progress and results on cloud infrastructure.
Funktionen
Tools
17
Tools
attach_input_layer
Attach Input Layer
Attach a GeoJSON you uploaded to GeoNode as the project's boundary, friction, inflow, rainfall, structure or mesh_region 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/
â 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 â running â finished | failed), reads the
new dataset's pk, and PATCHes it onto the project's DEFAULT row of that
kind ('Boundary 01' ⦠'MeshRegion 01' â 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).
`outcome` is exactly one of: `attached` (row_id, gn_layer, dataset_pk,
dataset_alternate â the WFS typename â and every row id seen);
`timed_out` (the import is still running: call again with the same
arguments); `upload_failed` (the execution record, incl. its log, is
returned verbatim â 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` and kind `culvert` â no
REST create path exists for either at HEAD (TASK-3040 AC6), and culvert
flow is not conveyed by run_anuga, 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 â create that
gauge with create_time_series under the exact same name.
Eingabeschema
{'type': 'object', 'required': ['project_id', 'kind', 'execution_id'], 'properties': {'kind': {'type': 'string', 'description': 'Which input the uploaded layer is: boundary, friction, inflow, rainfall, structure or mesh_region. breakline and culvert are refused (see below).'}, 'project_id': {'type': 'integer', 'description': 'The project ID'}, 'execution_id': {'type': 'string', 'description': '`execution_id` returned by your multipart POST to <origin>/api/v2/uploads/upload/'}, 'timeout_seconds': {'type': 'integer', 'default': 240, 'description': 'How long this call keeps polling the upload before it returns `timed_out` (default 240, ceiling 280 â\x80\x94 the prod /mcp/ proxy cuts a call at 300 s). 0 = one status read, no waiting.'}, 'poll_interval_seconds': {'type': 'number', 'default': 5.0, 'description': 'Seconds between polls (default 5)'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
build_scenario
Build Scenario
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 â refused: a build
needs the EDITOR role.
2. Re-call checks on `latest_run` (a re-POST is NOT deduplicated after
`built`/`complete` â it would dispatch a duplicate build): no run â
proceed; run `created`/`building` â resume polling, no POST; run
`built`/`queued`/`computing`/`processing`/`complete` with
`latest_run_is_valid` not false â return that state, no POST unless
rebuild=true; run `error`/`cancelled`, or `latest_run_is_valid` false
(the scenario was edited since the build) â 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 â 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` â 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) â the tool resumes polling that run.
5. On 202 poll the detail's `computed_status` (created â building â
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 â step 2 resumes polling the same run, it never POSTs twice â
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 â an errored latest run is rebuilt).
Units: `resolution` on the SCENARIO is a LENGTH in metres â ANUGA
maximum_triangle_area = resolution²/2 (run_utils.py:227/:290; FloatField
default 100, not nullable; 0 makes the estimate None) and the same value
becomes the raster cell size; a MeshRegion FEATURE's `resolution` is
consumed by the mesher as an AREA (max_triangle_area, m²) while the
estimate prices it as a length, so attached regions mesh ~15x more than
estimated (Towradgi 100/36/8 m² regions: estimate ~18k, mesh ~283k); the
smallest MeshRegion value becomes the raster cell size.
Eingabeschema
{'type': 'object', 'required': ['project_id', 'scenario_id'], 'properties': {'confirm': {'type': 'boolean', 'default': False, 'description': 'Required (true) when the estimate is above 100,000 triangles â\x80\x94 the tool refuses first and tells you the number. Default false.'}, 'rebuild': {'type': 'boolean', 'default': False, 'description': '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': {'type': 'integer', 'description': 'The project ID'}, 'scenario_id': {'type': 'integer', 'description': 'The scenario ID from create_scenario'}, 'timeout_seconds': {'type': 'integer', 'default': 240, 'description': 'How long this call keeps polling before it returns `timed_out` (default 240, ceiling 280 â\x80\x94 the prod /mcp/ proxy cuts a call at 300 s). 0 = one status read, no waiting.'}, 'poll_interval_seconds': {'type': 'number', 'default': 5.0, 'description': 'Seconds between polls (default 5)'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
cancel_run
Cancel Run
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).
Eingabeschema
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'integer', 'description': 'The run ID to cancel'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
create_project
Create Project
Create a new ANUGA project. Returns the project record including its id.
The caller's own account becomes the owner. `projection` is the projected
CRS every scenario in the project is meshed and run in â pick the UTM zone
covering the site. Next step for a new project: presign_terrain_upload.
Eingabeschema
{'type': 'object', 'required': ['name', 'projection'], 'properties': {'name': {'type': 'string', 'description': 'Project name'}, 'projection': {'type': 'string', 'description': "Working CRS as an EPSG string, normally the UTM zone of the site, e.g. 'EPSG:32756' (WGS 84 / UTM 56S)"}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
create_scenario
Create Scenario
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 â the create response carries NO estimate; the detail's
`mesh_triangle_count_estimate` (+ `_breakdown`) does. Returns a compact
record: id, name, the FK ids as stored, resolution, duration,
`computed_status` (`created` = no run yet), the estimate and its
breakdown, 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 is a LENGTH in metres â ANUGA
maximum_triangle_area = resolution²/2 (run_utils.py:227/:290; FloatField
default 100, not nullable; 0 makes the estimate None) and the same value
becomes the raster cell size; a MeshRegion FEATURE's `resolution` is
consumed by the mesher as an AREA (max_triangle_area, m²) while the
estimate prices it as a length, so attached regions mesh ~15x more than
estimated (Towradgi 100/36/8 m² regions: estimate ~18k, mesh ~283k); the
smallest MeshRegion value becomes the raster cell size.
The server does NOT validate that the FK ids belong to `project_id` â
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.
Eingabeschema
{'type': 'object', 'required': ['project_id', 'name', 'resolution', 'duration'], 'properties': {'name': {'type': 'string', 'description': 'Scenario name'}, 'inflow': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Inflow row id (optional; the build needs an inflow OR a rainfall)'}, 'terrain': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Terrain id (get_terrain â\x86\x92 terrain.id); the build fails without one'}, 'boundary': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Boundary row id (attach_input_layer kind=boundary â\x86\x92 row_id)'}, 'duration': {'type': 'integer', 'description': 'Simulation duration in seconds (e.g. 43200 = 12 h)'}, 'friction': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Friction row id (optional)'}, 'rainfall': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Rainfall row id (optional; the build needs an inflow OR a rainfall)'}, 'structure': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Structure row id (optional)'}, 'project_id': {'type': 'integer', 'description': 'The project ID'}, 'resolution': {'type': 'number', 'description': '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': {'type': 'string', 'default': '', 'description': 'Free-text description (optional)'}, 'mesh_region': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': "MeshRegion row id (optional). Leave UNSET unless you want the regions' finer meshing â\x80\x94 see the units note: they mesh ~15x more than estimated."}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
create_time_series
Create Time Series
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 â the API answers 500 (not 400) to a malformed row.
Returns a compact record â id, name, series_type, units, timezone,
row_count, http_status â 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.
Eingabeschema
{'type': 'object', 'required': ['project_id', 'name', 'data'], 'properties': {'data': {'type': 'object', 'description': '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.', 'additionalProperties': True}, 'name': {'type': 'string', 'description': 'Series name, kept VERBATIM â\x80\x94 a rainfall polygon binds to its gauge by this exact name (its `data` property), so use the name the GeoJSON features carry'}, 'units': {'type': 'string', 'default': '', 'description': "Display label for the values, e.g. 'mm/hr', 'm^3/s', 'm' (optional)"}, 'source': {'type': 'string', 'default': '', 'description': 'Where the data came from, e.g. a gauge id or agency (optional)'}, 'timezone': {'type': 'string', 'default': 'UTC', 'description': "IANA timezone of the timestamps (default 'UTC'), e.g. 'Australia/Sydney'"}, 'project_id': {'type': 'integer', 'description': 'The project ID'}, 'description': {'type': 'string', 'default': '', 'description': 'Free-text description (optional)'}, 'series_type': {'type': 'string', 'default': 'hyetograph', 'description': 'One of hyetograph (rainfall depth/intensity â\x80\x94 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': {'type': 'string', 'default': '', 'description': 'Human-readable location of the gauge (optional)'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
finalize_terrain_upload
Finalize Terrain Upload
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 â reproject to UTM, publish
the layer + hillshade, style â which also seeds the project's six default
boundary, friction, inflow, rainfall, structure 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) â do not retry finalize until it has.
Eingabeschema
{'type': 'object', 'required': ['project_id', 'staging_key'], 'properties': {'title': {'type': 'string', 'default': '', 'description': 'Terrain title (default: the filename without .tif)'}, 'process_id': {'type': 'string', 'default': '', 'description': "`process_id` returned by presign_terrain_upload (pass it so the upload's progress record is reused; the API tolerates its absence)"}, 'project_id': {'type': 'integer', 'description': 'The project ID'}, 'staging_key': {'type': 'string', 'description': '`staging_key` returned by presign_terrain_upload'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
get_project
Get Project
Get details of a specific ANUGA project including its scenarios.
Returns the project name, projection (EPSG code), base map ID,
and configuration.
Eingabeschema
{'type': 'object', 'required': ['project_id'], 'properties': {'project_id': {'type': 'integer', 'description': 'The project ID'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
get_run
Get Run
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.
Eingabeschema
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'integer', 'description': 'The run ID'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
get_run_status
Get Run Status
Lightweight status check for a simulation run (fast, <50ms).
Use this for polling instead of get_run. Returns only: id, status,
progress_pct (0-100), eta_seconds, error_message, and compute_backend.
Poll every 5-10 seconds. Terminal states: complete, error, cancelled.
Eingabeschema
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'integer', 'description': 'The run ID'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
get_scenario
Get Scenario
Get scenario details including its `computed_status` and latest run.
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 â `created`
also means no run exists yet. A scenario must be `built` before it can be
run. The detail also carries `mesh_triangle_count_estimate` (+ its
`_breakdown`) and `latest_run_is_valid` (false after any edit since the
last build). A non-member reading a public project's scenario gets a
reduced record with no `computed_status`.
Eingabeschema
{'type': 'object', 'required': ['project_id', 'scenario_id'], 'properties': {'project_id': {'type': 'integer', 'description': 'The project ID'}, 'scenario_id': {'type': 'integer', 'description': 'The scenario ID'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
get_terrain
Get Terrain
Poll a terrain's import until it is `ready` (or `error`), bounded by timeout_seconds.
Returns `outcome` â 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) â plus the last `status` seen (creating â styling â ready | error),
`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 â 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 â 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, Structure 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.
Eingabeschema
{'type': 'object', 'required': ['project_id'], 'properties': {'project_id': {'type': 'integer', 'description': 'The project ID'}, 'terrain_id': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': "The terrain ID from finalize_terrain_upload. Omit to follow the project's newest terrain."}, 'timeout_seconds': {'type': 'integer', 'default': 240, 'description': 'How long this call keeps polling before it returns `timed_out` (default 240, ceiling 280 â\x80\x94 the prod /mcp/ proxy cuts a call at 300 s). 0 = one status read, no waiting.'}, 'poll_interval_seconds': {'type': 'number', 'default': 5.0, 'description': 'Seconds between polls (default 5)'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
list_projects
List Projects
List ANUGA simulation projects accessible to the authenticated user.
Returns a paginated list of projects with their names, projections,
and base map references.
Eingabeschema
{'type': 'object', 'properties': {'page': {'type': 'integer', 'default': 1, 'description': 'Page number (default 1)'}, 'page_size': {'type': 'integer', 'default': 100, 'description': 'Results per page, max 100 (default 100)'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
list_runs
List Runs
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.
Eingabeschema
{'type': 'object', 'required': ['project_id'], 'properties': {'page': {'type': 'integer', 'default': 1, 'description': 'Page number (default 1)'}, 'page_size': {'type': 'integer', 'default': 100, 'description': 'Results per page, max 100 (default 100)'}, 'project_id': {'type': 'integer', 'description': 'The project ID'}, 'status_filter': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Filter by status: created, building, built, queued, computing, processing, complete, error, cancelled. Omit for all.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
presign_terrain_upload
Presign Terrain Upload
Step 1 of a terrain import: get a presigned S3 PUT URL for a GeoTIFF DEM.
The agent moves the bytes itself â 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 Ã 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 â then get_terrain.
Eingabeschema
{'type': 'object', 'required': ['project_id', 'filename'], 'properties': {'size': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'File size in bytes (`stat -c %s <file>`). The API rejects > 5 GiB up front. Omit if unknown.'}, 'filename': {'type': 'string', 'description': "Base name of the GeoTIFF, e.g. 'dem.tif' (a name only â\x80\x94 never contents)"}, 'project_id': {'type': 'integer', 'description': 'The project ID'}, 'content_type': {'type': 'string', 'default': 'image/tiff', 'description': "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."}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
retry_run
Retry Run
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.
Eingabeschema
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'integer', 'description': 'The run ID to retry'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
start_simulation
Start Simulation
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 â queued â computing â processing â complete.
After starting, poll get_run_status to track progress. Returns 409
if the scenario is not in the correct state.
Eingabeschema
{'type': 'object', 'required': ['scenario_id'], 'properties': {'scenario_id': {'type': 'integer', 'description': 'The scenario ID to run'}, 'compute_backend': {'type': 'string', 'default': 'local', 'description': "Compute backend: 'local' (Celery), 'ec2' (dedicated instance), or 'batch' (AWS Batch spot, cheapest). Default: 'local'"}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'string'}}, 'x-fastmcp-wrap-result': True}
Verlauf
Letzte Tool-Änderungen
Hinzugefügt
build_scenario
23. September 2026 02:53
Hinzugefügt
create_scenario
23. September 2026 02:53
Hinzugefügt
attach_input_layer
23. September 2026 02:53
Hinzugefügt
create_time_series
23. September 2026 02:53
Hinzugefügt
get_terrain
23. September 2026 02:53
Hinzugefügt
finalize_terrain_upload
23. September 2026 02:53
Hinzugefügt
presign_terrain_upload
23. September 2026 02:53
Hinzugefügt
create_project
23. September 2026 02:53
Geändert
list_runs
23. September 2026 02:53
Geändert
retry_run
23. September 2026 02:53
Geändert
cancel_run
23. September 2026 02:53
Geändert
get_run
23. September 2026 02:53
Geändert
get_run_status
23. September 2026 02:53
Geändert
start_simulation
23. September 2026 02:53
Geändert
get_scenario
23. September 2026 02:53
Geändert
get_project
23. September 2026 02:53
Geändert
list_projects
23. September 2026 02:53
Hinzugefügt
list_runs
17. September 2026 12:35
Hinzugefügt
retry_run
17. September 2026 12:35
Hinzugefügt
cancel_run
17. September 2026 12:35
Hinzugefügt
get_run
17. September 2026 12:35
Hinzugefügt
get_run_status
17. September 2026 12:35
Hinzugefügt
start_simulation
17. September 2026 12:35
Hinzugefügt
get_scenario
17. September 2026 12:35
Hinzugefügt
get_project
17. September 2026 12:35
Hinzugefügt
list_projects
17. September 2026 12:35
Entdecken
Ähnliche MCP-Server
MDEngine
com.forcefieldsilicon/mdengine
Runs hosted GPU molecular-dynamics workloads using LAMMPS or OpenMM, with deck validation, job management, logs, billing, and dow…
agent-compute-ledger
io.github.jdhart81/agent-compute-ledger
Records and verifies agent compute energy and carbon usage in tamper-evident ledgers, validates Landauer-limit claims, and produc…
Cloud World Model
ai.cloudworldmodel/cloud-world-model
Creates and runs temporary cloud architecture simulations with traffic, failures, recovery, performance metrics, and cost estimat…
green-router
io.github.jdhart81/green-router
Estimates compute energy and carbon footprints, ranks compute backends by emissions, and issues verifiable certificates tied to o…
Zhijiangyun Cloud (智匠云)
cloud.artibot/zhijiangyun
Supports GPU training, inference, benchmarking, and robot data collection for embodied-AI systems.
BorealHost
ai.borealhost/mcp
Provides web hosting and infrastructure management, including site deployment, DNS, domains, containers, compute, backups, cachin…
Clink Forge
com.clinkforge/clink-forge
Provides pay-per-call access to attested government datasets, primarily CDC and HHS health data plus EPA air-quality observations.
workbench
com.seqbench/workbench
Provides computational molecular biology tools for DNA, RNA, and protein analysis, cloning, PCR, CRISPR, oligonucleotide design, …