Mike params
Skills + MCP server for Claude Code, Codex, Hermes, or OpenClaw - headless MIKE+ automated modelling and analysis (inspect, edit, run, read, plot), no GUI.
npx -y skills add Zhonghao1995/Agentic-MIKE-Plus --skill mike-paramsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Read and modify MIKE+ model parameters via the mike-plus MCP server — inspect or change values in any model table (pipe Diameter/Manning in msm_Link, node levels in msm_Node, catchment properties in msm_Catchment, etc.). Use when an agent must identify a current parameter and change it before re-running. Requires MIKE+ + license; mutating tools must run on a copy.
SKILL.md
2.0 KB, as published. Nobody here has run it
MIKE+ Parameters
Reads and edits values in the MIKE+ model database tables (via mikeplus). This is the "edit the model" capability that sits between mike-model (overview) and mike-runner (execute).
Tools
mike_get_values—{sqlite, table, columns?, muids?}→ current values. Read-only. Use to identify a parameter before changing it.mike_set_values—{sqlite, table, values, muids | all}→ applies the change and returns before/after for the affected rows. Mutates the database.
Common tables / columns
msm_Link— pipes/reaches:Diameter,Width,Height,Manning(Manning's M; higher = smoother),MaterialID,TypeNo.msm_Node— manholes/nodes:GroundLevel,InvertLevel,Diameter.msm_Catchment— catchments: area / imperviousness / runoff parameters.msm_Project— simulation setups (used bymike_run'ssimulation).
Conventions (safety)
- Always operate on a COPY —
mike_set_valueswrites to the database and mikeplus has no undo. - Scope every edit. Pass
muidsto target specific elements; only setall=truewhen you truly mean every row. - Confirm with the returned
before/after(or a follow-upmike_get_values) before re-running. - After editing, re-run with
mike_runand compare results to quantify the effect.
Orchestration (identify -> change -> re-run -> compare)
mike_model_info / mike_get_values -> identify current parameter
mike_set_values -> change it (on a copy) -> before/after
mike_run -> new .res1d
mike_results_summary / read -> compare against baseline