Skip to content
Tresca

Agentic SWMM skills

SkillCommunity

SWMM skills and MCP servers for building, running, calibrating and auditing stormwater models. By Zhonghao Zhang.

31 starsUpdated 9 days agoGitHub data from 5 Nov 2026

At a glance

Type
Skill
Works with
EPA SWMM
Tool versions
Not stated in its documentation
Operating systems
Windows, macOS, Linux
Needs a EPA SWMM licence
No
AI clients documented
Claude Code, Codex, OpenClaw, Hermes, OpenCode
Licence
MIT
Language
Python
Release status
pre 1 0

What it can do

  • Separate skills for GIS preprocessing, network building, parameters, climate inputs, running, plotting, calibration, uncertainty, water quality, design review and reporting.
  • Matching MCP servers for the builder, network, parameter, climate, calibration, GIS and audit steps.
  • Writes provenance and audit records for each run so results can be traced and reproduced.
  • Can start from SWMMCanada or SWMManywhere to generate a model for an area.

Limitations

  • Pre-1.0 (v0.9.5 at check).
  • The skills carry the workflow; the solver, CLI and MCP servers need the separate project install.

Install

npx skills add Zhonghao1995/agentic-swmm-workflow

Source: github.com/Zhonghao1995/agentic-swmm-workflow#codex--claude--openclaw--hermes-ready

MCP servers and skills run code on your computer. Review the source before installing.

AI-generated models, drawings and results must be checked by a qualified engineer before use.