Zhonghao1995/Agentic-MIKE-Plus

**A headless, natural-language-driven, automated modelling workflow for MIKE+.**
**Skills + an MCP server** for Claude Code, Codex, Hermes, or OpenClaw: describe a goal in plain language and the agent inspects, edits, runs, reads, and plots a MIKE+ model. Automated modelling and analysis, end to end, without ever opening the GUI.
> [!TIP]
> **Need a model to run? SWMMCanada builds one anywhere in Canada.**
> It is the upstream, open-data model builder for this agentic workflow: draw an area on a map and it assembles a ready-to-run stormwater model from Canadian open data (real municipal storm networks for 8 cities, synthesized everywhere else), giving the agent a real network to run, edit, read, and plot. Try the hosted demo with no install at **swmm.h2ox.me**, or see the project at **h2ox.me**.
> Experimental / pre-release. One MCP server + skills wrapping DHI's Python stack (mikeplus / mikeio / mikeio1d). Verified end to end on the MIKE+ 2026 Sirius_RTC example. Sibling of agentic-swmm-workflow.
Install: just tell your agent
It is the AI era. You don't wire this up by hand. Paste this to your AI coding agent (Claude Code, Codex, Hermes, OpenClaw):
Needs **Python 3.11 (x64)**. Two install profiles:
- **Read & plot.** License-free and cross-platform: pip install -e . (no mikeplus).
- **Run & edit too.** Windows + a licensed **MIKE+ 2026**: pip install -e ".[run]" (or pip install -r requirements.lock for the exact pinned environment).
mikeplus is an optional [run] extra, so teammates who only read results or make figures install nothing license-bound.
Why it matters
- **Natural-language-driven.** Describe the task in plain words; the agent plans and runs it: no scripting, no GUI clicking. (A sub-agent did this autonomously.)
- **Fully headless.** Runs with no GUI, on a workstation, a server, in CI, or under an agent. Built for batch and scenario automation.
- **MCP-native and portable.** One server speaks the Model Context Protocol; works with **Claude Code, Codex, Hermes, or OpenClaw** via a single config line, and installs with pip.
- **Low barrier to share.** Reading results and plotting need no MIKE+ license; only running or editing does. Teammates analyse model output with nothing but pip install.
- **Reproducible & tested.** Deterministic tools, structured-JSON output, a pinned lockfile, and a license-free unit-test suite in CI, verified on a real model, not a chat-to-model black box.
- **Engine-agnostic and extensible.** Results use a common schema (ready to sit beside SWMM and LSTM); add a tool or skill by dropping in a file.
How it works
Skills (markdown playbooks) tell the agent *when and how*; the agent calls **MCP tools**; each tool runs in an isolated **worker subprocess** that imports only mikeplus *or* mikeio*: the two cannot share a process. The server itself imports neither.
Tools (one server, mike-plus)
| Tool | Does | License |
|---|---|---|
| mike_model_info | model overview: simulations, scenarios, model type, element counts | yes |
| mike_set_scenario | activate an existing scenario (verified by re-opening the model) | yes |