# Hydrata - ANUGA Flood Simulation

This MCP server runs ANUGA flood models in Hydrata Cloud, reports run progress, and returns simulation results. Use it when an agent needs to manage flood scenarios.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: Hydrata
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Hydrata/hydrata-mcp-server
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/hydrata-anuga-flood-simulation

## What it does

The server connects an MCP client to Hydrata Cloud over Streamable HTTP. An agent can create ANUGA projects, register a projection, prepare terrain and input layers, create time series, and build scenarios. It can then start, poll, cancel, or retry a run and inspect its logs and result layers.

Each tool call needs the caller’s Hydrata agent key with `read`, `draft`, or `launch` access. Hydrata checks that credential against the user’s project permissions. Without an accepted key, requests receive `401`; external accounts also cannot connect through a self-serve flow yet. A run above the key’s monthly spend limit stops before compute and returns a browser consent link.

Terrain and input data must be prepared first. `presign_terrain_upload` provides a URL for the agent to upload a GeoTIFF, while `attach_input_layer` links an uploaded GeoJSON dataset to the project. Scenario builds expose a mesh estimate and can require `confirm=true` for a large mesh.

## Requirements
- Remote server: `https://hydrata.com/mcp/`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http hydrata-mcp-server https://hydrata.com/mcp/
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add hydrata-anuga-flood-simulation --url https://hydrata.com/mcp/
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "hydrata-anuga-flood-simulation": {
            "url": "https://hydrata.com/mcp/"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "hydrata-anuga-flood-simulation": {
            "type": "http",
            "url": "https://hydrata.com/mcp/"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http hydrata-anuga-flood-simulation https://hydrata.com/mcp/
```

## When to use it
- run a flood simulation from an ANUGA scenario
- create a project with an EPSG projection
- attach boundary, building, or culvert GeoJSON data
- poll a run until its status or error is available
- inspect simulation logs and result layers

## Example prompts
- Create an ANUGA project with the required EPSG projection and prepare a flood scenario.
- Attach the uploaded GeoJSON as a `boundary` layer, then build the scenario and show its mesh estimate.
- Start the scenario run and keep checking its status until it finishes or reports an error.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md