Stella MCP Server

This is particularly useful for: - Teaching system dynamics modeling - Rapid prototyping of models through natural language - Batch creation or

Local serverstdioPython

What is the Stella MCP Server?

This is particularly useful for: - Teaching system dynamics modeling - Rapid prototyping of models through natural language - Batch creation or modification of

Configuration and credentials

  • Python 3.10+ - mcp>=1.19.0,<2

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
permissivedefault): continue with warnings
strictfail on compatibility issues
create_modelCreate a new model with name and time settings (start, stop, dt, method)
set_sim_specsUpdate simulation time settings on an existing model
read_modelLoad an existing .stmx file
save_modelSave model to a .stmx file
delete_modelRemove a model from the workspace (saved files untouched)
list_templatesList built-in and user-defined templates (supports source/query/tag filters)
get_template_infoGet detailed metadata for one template
load_templateLoad a template as a model in the current workspace
save_as_templateSave the current model as a reusable user template (optional description/tags)
build_modelCreate and populate a model in one call (atomic batch)
add_variablesAdd multiple variables/connectors/modules to an existing model (atomic batch)
add_stockAdd a stock (reservoir) with initial value and units
add_flowAdd a flow between stocks with an equation
add_auxAdd an auxiliary variable (parameter or calculation)
update_stockUpdate stock fields while preserving relationships
update_flowUpdate flow fields while preserving stock links
update_auxUpdate auxiliary variable fields
add_connectorAdd a dependency connector between variables
sync_connectors_from_equationsAdd missing dependency connectors inferred from equations
set_connector_routingSet connector angle and explicit waypoint routing metadata
rename_variableRename a stock/flow/aux and update references in equations/connectors/modules
delete_variableDelete a stock/flow/aux with consistency checks and cleanup
create_moduleCreate a logical module/group of variables
add_to_moduleAdd variables to an existing module/group
remove_from_moduleRemove variables from a module/group
rename_moduleRename a module/group
delete_moduleDelete a module/group
set_module_viewSet explicit module box position/size on the diagram
set_module_styleSet module box style (border/background/font/label side) on the diagram
auto_place_module_boxesAuto-place module boxes around their members
create_workspaceCreate an isolated workspace, optionally with a caller-selected lifetime
revoke_workspaceRevoke a workspace and discard its in-memory models
list_modelsList available workspace model IDs and indicate the current model
inspect_modelReturn a structured model summary for agent inspection
list_modulesList modules/groups in the current model
list_connectorsList connector IDs, endpoints, angles, and routing metadata
list_variablesList all stocks, flows, and auxiliaries
validate_modelCheck for errors (undefined variables, missing connections, etc.)
get_model_xmlPreview the XMILE XML output
render_diagramRender the model as an SVG stock-and-flow diagram
simulateRun the model via PySD and return time series + summaries (sim extra)
compare_scenariosRun named what-if override sets against a baseline and report deltas (sim extra)
sensitivity_analysisSweep parameters one-at-a-time and rank their effect on an output metric (sim extra)
calibrateFit constant parameters to an observed time-series (inverse of simulate) (sim extra)

How to install the Stella MCP Server

{
  "mcpServers": {
    "stella": {
      "command": "uvx",
      "args": [
        "stella-mcp"
      ]
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

  • Python 3.10+ - mcp>=1.19.0,<2

Example prompts to try

  • “Use Stella MCP to Requirements.”
  • “Use Stella MCP to Templates.”

Frequently asked questions

This is particularly useful for: - Teaching system dynamics modeling - Rapid prototyping of models through natural language - Batch creation or modification of Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.