Stella MCP Server

A vendor-neutral Model Context Protocol (MCP) server for creating and manipulating Stella system dynamics models. Any compliant MCP client can build, read, validate, and save .stmx files in the XMILE format; optional host features still vary.

What is this for?

Stella is a system dynamics modeling tool used for simulating complex systems in fields like ecology, biogeochemistry, economics, and engineering. This MCP server allows AI assistants to:

• Create models from scratch - Build stock-and-flow diagrams programmatically
• Read existing models - Parse and understand .stmx files
• Validate models - Check for errors like undefined variables or missing connections
• Modify models - Add stocks, flows, auxiliaries, and connectors
• Save models - Export valid XMILE files that open in Stella Professional

This is particularly useful for:

• Teaching system dynamics modeling
• Rapid prototyping of models through natural language
• Batch creation or modification of models
• Documenting and explaining existing models

Installation

From PyPI

pip install stella-mcp

From source

git clone https://github.com/bradleylab/stella-mcp.git
cd stella-mcp
pip install -e .

Requirements

• Python 3.10+
• mcp>=2.0.0,<3

Configuration

Via uvx (no install required)

If you have uv installed, the lowest-friction configuration runs the published package directly:

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

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "stella": {
      "command": "stella-mcp"
    }
  }
}

Claude Code

Add to your .claude/settings.json:

{
  "mcpServers": {
    "stella": {
      "command": "stella-mcp"
    }
  }
}

Development mode

If running from source:

{
  "mcpServers": {
    "stella": {
      "command": "python",
      "args": ["-m", "stella_mcp.server"],
      "cwd": "/path/to/stella-mcp"
    }
  }
}

Recommended Agent Workflow

For a new model:

1. On MCP 2026-07-28, call create_workspace and carry the returned workspace_id through stateful calls. Legacy stdio clients may omit it.
2. build_model with a stable model_id and the full set of stocks, auxiliaries, and flows in one call (connector sync and validation run by default, so the response doubles as an inspection).
3. Fix validation errors with update_*, rename_variable, or delete_variable.
4. Extend incrementally with add_variables (batch) or the single-add tools.
5. simulate to sanity-check behavior (requires the sim extra).
6. Save with save_model.

For imported models:

1. read_model with compat_mode="permissive" to inspect warnings.
2. Run inspect_model to understand model structure.
3. Use compat_mode="strict" before final save when round-trip fidelity matters.

Available Tools

Model Creation & I/O

Templates

Model Building

Notes:

• MCP 2026-07-28 clients call create_workspace once and include its returned workspace_id in stateful calls. Modern tool discovery marks that field as required on stateful tools. The ID routes application state; it is not an authorization credential.
• Supported legacy stdio clients may omit workspace_id and use one process-local compatibility workspace; legacy discovery keeps the field optional.
• Tools accept optional model_id so one workspace can manage multiple models safely.
• create_model and read_model set the workspace's current model_id and return it.
• add_flow and add_aux support optional graphical_function payloads (ypts plus exactly one of xscale or xpts).
• add_stock/add_flow/add_aux reject duplicate variable names across variable types; add_connector requires both variables to exist.
• set_connector_routing can target a connector by connector_uid or by from_var + to_var.
• save_model and get_model_xml accept auto_layout (default true) and resolve_layout_violations (default false).
• save_model, get_model_xml, and render_diagram return the latest layout viewport, metrics, and warnings in structured content. Their text result names any non-clean layout warning codes.
• read_model, save_model, and get_model_xml accept compat_mode:
  • permissive (default): continue with warnings
  • strict: fail on compatibility issues
• set_module_style updates module view styling and persists those attributes in XMILE view <group .../> elements.
• save_as_template writes user templates to ~/.stella-mcp/templates by default (override via STELLA_MCP_TEMPLATE_DIR) and stores metadata in a .meta.json sidecar.
• Tool failures return structured MCP errors with error.code, error.category, and error.message.
• Every successful tool result retains readable text and supplies schema-validated structuredContent described by its JSON Schema 2020-12 outputSchema.

Workspace Lifecycle

Model Inspection

Batch Building

build_model creates and populates a model in one call. Items apply in the order stocks → auxs → flows → connectors → modules; the whole batch is all-or-nothing, and on failure the error names the failing item (error.stage + error.index). The same item arrays work on an existing model via add_variables.