mike_run

MCP tool from Agentic MIKE Plus by Zhonghao1995

run a simulation headless, return .res1d + a parsed QA status (completed / errors / warnings)

How to use it

mike_run is exposed by the Agentic MIKE Plus MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the mike_run tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Agentic MIKE Plus

$claude mcp add mike-plus -- "<abs-repo>\.venv\Scripts\python.exe" -m mikeplus_mcp.server

FULL AGENTIC MIKE PLUS LISTING

Other tools in Agentic MIKE Plus (7)

mike_import_swmm

import an EPA SWMM (or EPANET) .inp into a new MIKE+ model: the SWMMCanada bridge

mike_manifest_write

provenance manifest: model, inputs, edits, run QA, results, figures, each with sha256

mike_model_info

model overview: simulations, scenarios, model type, element counts

mike_rain_to_dfs0

rainfall CSV to a MIKE+ .dfs0 (intensity, read-back verified)

mike_results_compare

baseline vs scenario: delta peak / volume / timing, RMSE, NSE; or every element ranked by change

mike_results_flooding

which nodes flood: peak water level vs ground level, ranked

mike_set_scenario

activate an existing scenario (verified by re-opening the model)