LabscoMCP early access ↗
Zhonghao1995MCP SERVER

Agentic SWMM

Natural-language stormwater modelling with deterministic EPA SWMM runs and an audit trail behind every number.

by Zhonghao1995 ↗Physical Sciences & Scientific ComputingCommunity

LABSCO SUMMARY

Natural language on the front, deterministic SWMM underneath.

The discipline is what makes this usable for real work: model files, runs, QA checks and provenance stay on disk as artefacts you can re-run and audit, so an agent-driven run is reproducible rather than a chat transcript. The published case where the model named its own errors as disqualifying, rather than reporting numbers from a dry week, is the behaviour to look for.

What it is

A verification-first framework for reproducible stormwater modelling. You describe a modelling goal in English; model construction, SWMM execution, QA checks and reporting run as deterministic, inspectable steps that leave artefacts behind. The MCP servers and skills work with the project's own runtime or with Codex, Claude Code, OpenClaw and Hermes.

What you get

  • Modelling operations exposed both as tools and as CLI verbs on the same engine: run_swmm_inp runs a model, audit_run produces the provenance record, note and diagnostics, review_run checks a run against the rulebook
  • Calibration and scenarios — swmm_calibrate_search and swmm_calibrate_sceua against an observed CSV, run_climate_scenarios to compare the model under precipitation-scaled scenarios
  • Inputs and outputs — generate_design_storm for a design rainfall series, plot_run for hydrographs, map_run for the network map, generate_report for a client-ready document
  • Every run leaves reusable artefacts: the SWMM input file, .rpt and .out outputs, manifests and command traces, QA summaries and parsed peak-flow metrics, plus experiment_provenance.json, comparison.json and experiment_note.md
  • Real networks upstream — SWMMCanada covers 35 Canadian cities, SWMManywhere synthesises elsewhere
  • Skills install into any skills-aware runtime with npx skills add Zhonghao1995/agentic-swmm-workflow

Requirements

One-line installers for macOS and Linux (curl -fsSL https://aiswmm.com/install.sh | bash) or Windows PowerShell, then aiswmm to launch the runtime; a pinned Docker image runs it with no local install. pip install aiswmm==0.9.3 is the third path. After install, aiswmm setup lists ten LLM provider routes and detects what is already running — three need no API key, including a local gateway. Never paste API keys into the conversation; store them as documented. Pre-1.0, stable at v0.9.3. MIT.

Setup effort

Build from source — git clone https://github.com/Zhonghao1995/agentic-swmm-workflow.git

See installation options