Hydrata - ANUGA Flood Simulation

com.hydrataPublished by hydrata.comOfficial publisherv0.2.2Updated Nov 4, 2026

Run ANUGA flood simulations, track progress, and retrieve results on Hydrata Cloud.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureData & Analytics

Overview

Hydrata - ANUGA Flood Simulation's hosted MCP server (hydrata.com), published by hydrata.com; OAuth sign-in required; Streamable HTTP.

No AI overview yet: these facts come from the registry entry and the server itself.

Publisher
hydrata.com
Endpoint
hydrata.com
Last checked

Installation

In SourceWeft

  1. Open Hydrata - ANUGA Flood Simulation in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.hydrata%2Fhydrata-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "hydrata-anuga-flood-simulation": {
      "type": "http",
      "url": "https://hydrata.com/mcp/"
    }
  }
}

README

hydrata-mcp-server

[License: MIT]

MCP server for Hydrata Cloud — build ANUGA flood models from terrain and input layers, run simulations, track progress, and retrieve results through the Model Context Protocol.

Connect and authenticate

Endpoint: https://hydrata.com/mcp/ — Transport: Streamable HTTP.

Every tool call needs the caller's own hydrata.com credential: an agent key (Authorization: Bearer hk_…), a named, revocable grant at one of three levels (read < draft < launch) that the account owner creates — and can revoke, one at a time or all at once — on the site's Agent keys page (/agents/). The server holds no identity and no key store of its own: it checks only the shape of the credential (an hk_ prefix, or with the connect flow configured a JWT-shaped token) and forwards the one accepted Authorization header unchanged to the Hydrata REST API, where Django verifies it on every tool call (for a connect-flow token: signature, issuer, audience, expiry and the live grant; for an agent key: the stored hash and the live grant) — so results are scoped by the real user's project permissions and the key's level, and the audit trail names them. Every JSON-RPC request — initialize, tools/list and ping as well as tools/call — that does not carry exactly one accepted credential (an agent key, or with the one-click connect flow configured its access token) is answered with 401, a JSON-RPC error -32001 and WWW-Authenticate: Bearer realm="hydrata.com" (plus resource_metadata="…" when the connect flow is configured) before it reaches the MCP SDK: no Authorization header, HTTP Basic, or any other Bearer token such as a GeoNode OAuth token. Agent keys and connect-flow tokens both map to an agent grant, so both are subject to the grant's level, the account's pause switch, the spend limit and the agent activity log. The 401 on the first request is what tells an OAuth-aware client such as claude.ai that the server needs sign-in (TASK-3987), so the tool catalog is not served to a request without a credential of an accepted shape; for initialize, tools/list and ping that credential is checked for shape only, not verified. The one exception (TASK-4177): MCP catalog crawlers whose User-Agent matches an allowlist (HYDRATA_MCP_DISCOVERY_USER_AGENTS, default mcptry.com indexer,SmitheryBot) may run initialize, ping and tools/list with no Authorization header, so catalogs can show the tools; tools/call always needs a credential, and real clients never match, so they still get the 401 and the sign-in default. Each claim about this server's security behaviour is cited to code or a test in docs/security-model.md; to report a vulnerability see SECURITY.md. A body that is not JSON-RPC is left to the SDK's own error, and a GET on the endpoint is answered 405. A static MCP Server Card (SEP-2127), built from server.json, is served without credentials at GET https://hydrata.com/mcp/server-card. The catalog icon, a 512×512 PNG of the Hydrata mark, is served the same way at GET https://hydrata.com/mcp/icon.png and listed in server.json and serverInfo.icons.

Anyone with a hydrata.com account can connect. There are two ways in, and both give the assistant a named, revocable permission at one access level (Read, Draft or Launch):

  • One-click connect (OAuth) — for claude.ai, ChatGPT and any MCP client that can add a connector by URL. Add https://hydrata.com/mcp/ as a custom connector, sign in with your Hydrata account, name the connection and choose its level. The assistant never sees your password.

  • Agent key — for Claude Code, scripts and any client that can send an HTTP header. Create a key on the Agent keys page (https://hydrata.com/agents/) and send it as Authorization: Bearer hk_…. In Claude Code:

    bash
    claude mcp add --transport http hydrata https://hydrata.com/mcp/ --header "Authorization: Bearer hk_YOUR_KEY"

    Do not add --scope project: that writes the key into the project's shared .mcp.json.

Keys and connections are listed, and revoked, on the same Agent keys page. A run that costs money waits for your consent in the browser unless the key's monthly spend limit covers it. Full guide: Connect an AI assistant in the Hydrata MCP docs.

Tools

Version 0.2.2 exposes forty-two tools, all listed below; nineteen of them only read. Every tool carries MCP annotations: a title and explicit boolean readOnlyHint, destructiveHint, idempotentHint and openWorldHint (openWorldHint is false on every tool: they reach only your Hydrata account). destructiveHint is true only on cancel_run, delete_time_series and delete_observation.

ToolDescription
list_projectsList ANUGA simulation projects (paginated)
get_projectGet one project — name, projection, visibility, your role, base_map — plus ui_url, the link that opens its map
get_scenarioGet a scenario's compact state — computed_status, its inputs (terrain, boundary, friction, inflow, rainfall, building, mesh region, culvert, resolution, duration), the mesh-triangle estimate + breakdown, the price (compute_cost_estimate, vcpu_hours_estimate) and the latest run's id/status/error — never the raw detail
start_simulationStart a flood simulation (local/EC2/Batch backends); the returned run record has its presigned download links elided; hand-back link opens the run. A run over the agent key's monthly spend limit (default $0), or one Hydrata cannot price, is not started: the tool relays Hydrata's CONSENT_REQUIRED at once with the consent_url the person opens in their browser (consent_timeout_seconds > 0 also polls the run for their click)
get_run_statusLightweight status poll (<50ms); phase is never empty (preparing_inputs while a computing run has no progress yet)
get_runFull run details with timing, log and result layers; presigned s3_*_url download links are elided
get_flow_hydrographFlow (Q) across a line you draw, at every frame of a completed run: peak, time of peak, volume and a mass balance, from the run's playback store (the model's flow, not a gauge reading)
cancel_runCancel an in-flight simulation; hand-back link opens the scenario
retry_runRetry a failed simulation (rebuilds the scenario as a new run); hand-back link opens the scenario
list_runsList runs across a project (with status filter); presigned s3_*_url download links are elided from every row
list_inputsEvery input row of a project per kind (boundary, friction, inflow, rainfall, building, mesh region, culvert) — row id, title, dataset, WFS typename and whether it has features — so the agent never has to probe files
list_time_seriesA project's time series — id, name, type, units, row count and first/last timestamp; the data rows are never returned
create_projectCreate an ANUGA project with a name and EPSG projection; returns its base_map and the ui_url of its map
presign_terrain_uploadReturn a presigned URL + key so the agent PUTs the terrain GeoTIFF itself (no file bytes pass through MCP)
finalize_terrain_uploadRegister the uploaded terrain; the import chain seeds the project's six default boundary/friction/inflow/rainfall/building/mesh-region rows (no culvert row: attach_input_layer creates 'Culvert 01' on demand)
get_terrainPoll the terrain until it is ready (bounded; timed_out means call again); phase is never empty; summary = WGS84 bbox, elevation min/max, nodata fraction, native CRS; the link frames the DEM
list_terrain_sourcesThe terrain Hydrata can fetch for a site, finest first (Copernicus GLO-30 worldwide, finer regional LiDAR such as Geoscience Australia 5 m where it has data), with coverage, size cap, vertical datum and licence
create_terrain_from_sourceHave Hydrata fetch, reproject and publish a DEM from one of those sources, then wait for the import like get_terrain
sample_terrainGround level at points (null where the terrain has no data), to place a culvert, inflow or boundary on the ground
terrain_profileGround along a line (a cross-section) with the lowest sample, to find where a channel runs
create_time_seriesCreate a time series (rain gauge, hydrograph or tide/stage — series_type and units are top-level fields) from {"rowData": [...]}; a rainfall polygon binds to its gauge by the series name; summary = row count + first/last timestamp; the link opens the Hydrology panel
update_time_seriesCorrect a time series (PATCH); the same validation as create, and a series a built scenario uses sends that scenario back for rebuild and review
delete_time_seriesDelete a time series (Manager role); refused while a layer feature still uses it, naming the layer and feature
attach_input_layerAttach a GeoJSON dataset the agent already uploaded as the project's boundary/friction/inflow/rainfall/building/mesh-region or culvert layer (kind structure = deprecated alias of building); culvert attributes are mapped onto the culvert fields with defaults filled, and culvert_problems lists what the build will still refuse; breakline is refused; summary = feature count (WFS hits) + WGS84 bbox + whether the map now shows the layer; the link opens Inputs and frames the layer
describe_input_kindsWhat each input layer kind looks like (geometry, properties, allowed values, a minimal example), generated from the definitions the build reads
read_input_layerRead a project input layer's features as GeoJSON, each with its author (a person, or the agent that wrote it)
write_input_layerWrite an input layer (boundary, friction, inflow, rainfall, building, mesh region or culvert) from GeoJSON sent in the call; target writes a separate row for a variant
request_input_uploadThe link where the person uploads a big input layer (over about 150 KB) in their browser: GeoJSON, zipped shapefile or GeoPackage up to 100 MB
create_scenarioCreate a draft scenario and return its mesh-triangle estimate and price (resolution — scenario and mesh-region — is a length in metres); the link opens the scenario
update_scenarioEdit a scenario's name, description, resolution, duration or attached inputs; never builds or runs, the changed scenario is marked stale
clone_scenarioCopy a scenario into a sibling for a variant (no run copied, nothing built), with overrides checked before the copy is made
build_scenarioBuild the scenario package; shows the estimate first and needs confirm=true above 100,000 triangles; polls computed_status to built; never re-posts a build that is in flight or already built (rebuild=true to force one); surfaces the server's 422 refusals (MESH_TOO_LARGE, BOUNDARY_NO_EXTERNAL, MESH_REGION_UNITS_UNMARKED) verbatim; a missing/empty/perimeter-less boundary sends the human to the map to draw or fix it; summary = triangle count + re-priced cost
create_observation_layerCreate a flood observation layer (project-level, never a scenario input) with its vertical datum (terrain, AHD, EGM2008, ellipsoidal, or local + datum_offset_m); waits for the map layer (ready, bounded); the link frames it in the Observations group
list_observationsA project's flood observation layers, or one layer's observations — fid, subtype, stage/depth, sigma, bound, observed window in UTC, datum status (unknown = not scored), photo_count and problems
add_observationsAdd Flood marks, Timed levels, Gauge records and Dry points (up to 200 per call; srid for native coordinates, entry_timezone for naive times); the API validates each one, refused rows come back with the field that is wrong while the rest land
update_observationEdit one observation (PATCH of the fields given; validated against the stored observation)
delete_observationDelete one observation and its photos
add_observation_photo_linkAttach a photo to an observation as a reference link only (stored, never fetched); a photo FILE is refused with the UI path — the engineer uploads files in the photo strip on the observation's form in the map
get_observation_comparisonHow a historic run compares with the project's flood observations: headline (figures at a tolerance, 0.3 m default; no pass or fail), statistics (n, within, bias, RMSE, weighted RMSE, MAE, max), Gauge record peak/timing/NSE, datum checks and one row per observation (residual = modelled - observed; unscored and excluded rows included). layer_id + fid narrow it to one observation with its exclusion history; Gauge records' modelled series are elided unless include_series. A design or unlabelled run reports has_comparison: false, not an error
set_observation_exclusionExclude one observation from a run's comparison with the engineer's reason (required: the tool refuses a blank one and the agent must ask), or include it again; logged with user and reason; returns headline_after
set_comparison_toleranceSave the project's default comparison tolerance (metres, above 0 and at most 5; Editor+). get_observation_comparison uses it unless tolerance is passed, which saves nothing
suggest_capabilityTell the Hydrata team about something the person asked for that no tool can do (read-only; the reply gives the words to say to the person; 20 a day per person)

The hand-back: the engineer signs off in the map

Every tool that changes something (create_project, finalize_terrain_upload, get_terrain, create_time_series, attach_input_layer, create_scenario, build_scenario, start_simulation, cancel_run, retry_run, the five flood observation writes, and the three comparison tools) also returns:

  • ui_url — https://<site>/catalogue/#/map/<base_map>?panel=…&layer=…&scenario=…&run=…, which opens the project map on the thing that changed (the Inputs panel framing the attached layer, the Hydrology panel, the scenario, the run);
  • summary — numbers the engineer can check (feature count and bbox, elevation range, row count and time span, triangle estimate and price);
  • say_to_user — the sentence the agent should relay.

The server's instructions tell the agent to hand the link to the user after each layer lands and to wait for the user before start_simulation. Refusals the user can fix in the map (no boundary, no External boundary edge) carry the link too. Every request the server forwards carries X-Hydrata-Client: mcp/<version> and X-Hydrata-Session: <uuid> — informational only (client-asserted), never used for authorship.

No tool accepts file contents inline. The agent moves the bytes itself — the terrain GeoTIFF to the presigned URL, a GeoJSON layer to the REST API upload endpoint — and hands the server the resulting key or upload id.

No read tool relays a presigned S3 URL. A run's result links are 6-hour capabilities carrying a temporary AWS credential, and the server forwards the caller's own credential rather than holding one, so a tool that echoed such a link would widen what an agent transcript is worth beyond what the caller asked for. Every read tool (and start_simulation) elides them, recursively, by key name (s3_*_url) and by value shape (any string carrying X-Amz-Signature / X-Amz-Security-Token, redacted in place so the rest of a log line survives); results stay viewable through the gn_layer_* WMS entries. presign_terrain_upload is the sole exception: its upload_url is the URL the caller explicitly asked for.

Typical workflow

Run a scenario that already exists:

list_projects → get_scenario → start_simulation → poll get_run_status → get_run

Import a model and run it:

create_project → presign_terrain_upload → PUT the GeoTIFF → finalize_terrain_upload → get_terrain→ create_time_series / attach_input_layer → create_scenario → build_scenario→ start_simulation → poll get_run_status → get_run

What is Hydrata?

Hydrata is a geospatial hydraulic modeling platform. It runs ANUGA flood simulations in the cloud — upload terrain data, configure scenarios, run simulations on managed compute (Celery, EC2, or AWS Batch), and visualise results on interactive maps.

ANUGA is an open-source hydrodynamic model developed by Geoscience Australia and the Australian National University. It solves the shallow water wave equations using finite volumes on an unstructured triangular mesh.

Development

bash
git clone https://github.com/Hydrata/hydrata-mcp-server.gitcd hydrata-mcp-serverpip install -e ".[dev]"pytest -v

Contributions welcome — see issues.

License

MIT

Source: README.md at commit d4d0970

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

4
  1. v0.2.2LatestNov 4, 2026
  2. v0.2.1Nov 3, 2026
  3. v0.2.0Sep 21, 2026
  4. v0.1.0Sep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts