Agentic MCP Server

Unified CLI for reproducible and auditable Agentic SWMM workflows.

Local serverstdioPython

What is the Agentic MCP server?

Unified CLI for reproducible and auditable Agentic SWMM workflows. That is what the agentic mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Agentic SWMM is an open-source, verification-first framework for reproducible and extensible stormwater modelling, starting with EPA SWMM. It connects QGIS-based preprocessing, upstream model generation from SWMMCanada inside Canada (real storm networks for 8 cities, synthesis anywhere else in the country) and SWMManywhere-based synthesis outside Canada, deterministic SWMM execution, QA checks, provenance tracking, calibration support, documentation, and modelling memory, while keeping human modellers in control.

  • Agentic SWMM for reproducible stormwater modeling: — the aiswmm runtime + Skills + MCP + SWMM, with a verification-first workflow and Obsidian-compatible audit trail
  • Five minutes, one command: — an Agentic SWMM workflow that is auditable, memory-informed, and agent-ready
  • Live demo (no install, offline case replay): — try it in the browser at aiswmm.com
  • Runtime-portable: — the Skills and MCP servers also work with Codex, OpenClaw, and Hermes Agent
  • Published research: — our paper is published in AI for Engineering (MDPI), June 9, 2026: read the paper

The tools it exposes

The server publishes 7 tools. What each one is for:

  • Runtime-portable — ** the Skills and MCP servers also work with Codex, OpenClaw, and [Hermes
  • Agent — guided, SWMM-grounded:** agents can coordinate tasks, while model execution stays deterministic, inspectable, and CLI-runnable
  • Verification — first provenance:** build, run, audit, and comparison stages emit traceable artifacts before outputs are treated as evidence
  • rainfall — runoff figures, calibration summaries, and fuzzy uncertainty summaries
  • Obsidian — ready modelling notes and modelling-memory summaries
  • Path — What it shows
  • Project — Role in the ecosystem

Getting it running

The server ships on npm as skills, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agentic's toolset — Runtime-portable, Agent, Verification and 4 more — is a fair guide to whether it matches your workflow. It is maintained by Zhonghao Zhang, Caterina Valeo; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agentic's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Runtime-portable** the Skills and MCP servers also work with [Codex](https://openai.com/codex/), [OpenClaw](https://github.com/openclaw/openclaw), and [Hermes Agent](https://github.com/NousResearch/hermes-agent).
Agentguided, SWMM-grounded:** agents can coordinate tasks, while model execution stays deterministic, inspectable, and CLI-runnable.
Verificationfirst provenance:** build, run, audit, and comparison stages emit traceable artifacts before outputs are treated as evidence.
rainfallrunoff figures, calibration summaries, and fuzzy uncertainty summaries
Obsidianready modelling notes and modelling-memory summaries
PathWhat it shows
ProjectRole in the ecosystem

How to install the Agentic MCP server

{
  "mcpServers": {
    "agentic-swmm-workflow": {
      "command": "npx",
      "args": ["-y", "skills"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Agentic to Runtime-portable.
  • Use Agentic to Agent.
  • Use Agentic to Verification.

Frequently asked questions

It connects Agentic to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (Runtime-portable, Agent, Verification, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentic directly.