text2sim-MCP-server
If you are the rightful owner of text2sim-MCP-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Text2Sim MCP Server is a multi-paradigm simulation engine that integrates with LLMs using the Model Context Protocol (MCP), supporting Discrete-Event Simulation (DES) and System Dynamics (SD).
Text2Sim MCP Server
Multi-paradigm Simulation Engine for LLM Integration
Text2Sim MCP Server is a simulation engine that supports multiple modeling paradigms, including Discrete-Event Simulation (DES) and System Dynamics (SD). It integrates with LLMs using the Model Context Protocol (MCP), enabling powerful simulation capabilities within natural language environments like Claude Desktop.
🚀 Features
-
Large Language Model (LLM) Integration
Create simulation models using plain English descriptions to LLMs. -
Multi-Paradigm Support
- Discrete-Event Simulation (DES) using SimPy for process-oriented models
- System Dynamics (SD) using PySD for feedback-driven continuous models
-
Multi-Domain Support
Build simulations for domains such as airport operations, healthcare, manufacturing, supply chains, and more. -
Flexible Model Configuration
- DES: Configurable entities with stochastic process logic
- SD: Stock-and-flow models with feedback loops and time-based equations
-
Real-Time Metrics
- DES: Performance indicators such as wait times and throughput
- SD: Time series data for stocks, flows, and auxiliaries
-
Secure Implementation
Uses regex-based parsing (noteval()) for processing distribution inputs and safe model execution.
🔧 Installation
Prerequisites
- Python 3.12 or higher
uvpackage manager
Install uv
On macOS and Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
On Windows (PowerShell):
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Learn more: astral-sh/uv
🛠️ Usage
Clone the repository
git clone https://github.com/IamCatoBot/text2sim-MCP-server.git
Integration with Claude Desktop
- Open:
Claude > Settings > Developer > Edit Config > claude_desktop_config.json
- Add the following block:
{
"mcpServers": {
"Text2Sim MCP Server": {
"command": "uv",
"args": [
"--directory",
"PATH_TO_TEXT2SIM_MCP_SERVER",
"run",
"mcp_server.py"
],
"env": {}
}
}
}
Note: If the
uvcommand is not found, runwhich uv(Unix) orGet-Command uv(PowerShell) and use the full path in the"command"field.
📚 API Reference
Overview
The MCP server provides tools for both Discrete-Event Simulation and System Dynamics modeling:
- Discrete-Event Simulation: Process-oriented modeling with SimPy
- System Dynamics: Stock-and-flow modeling with PySD
When using a Large Language Model (e.g. Claude) client, natural language prompts are translated into appropriate configurations via the Model Context Protocol (MCP).
🏗️ Architecture
Text2Sim is structured into modular components:
- MCP Server – Handles natural language requests via MCP.
- Discrete-Event Simulation (DES) Module
- Simulation Model – Core SimPy engine that executes process flows.
- Entity Class – Represents units flowing through the system.
- Process Steps – Encapsulate logic for each process stage.
- Metrics Collector – Gathers statistics like wait times and throughput.
- Secure Distribution Parser – Parses probability distributions safely.
- System Dynamics (SD) Module
- Model Registry – Manages available SD models.
- PySD Integration – Runs stock-and-flow models using PySD.
- Simulation Controls – Time steps, durations, and parameter adjustments.
- Results Formatter – Structures time series data for output.
For detailed documentation of each module, see:
🔐 Security Considerations
-
No
eval()usage
Regex-based parsing prevents arbitrary code execution. -
Input Validation
Distribution types, parameters, and model configurations are validated before execution. -
Robust Error Handling
Errors are reported cleanly without leaking internal state.
🤝 Contributing
Pull requests are welcome! Please fork the repo and submit a PR. Suggestions, bug reports, and feature ideas are always appreciated.
📄 License
This project is licensed under the MIT License. See the file for details.
