yusong652/pfc-mcp

Overview

An MCP server that connects AI agents to ITASCA PFC for running Discrete Element Method simulations through natural language. It enables agents to configure, execute, and retrieve simulation results via conversational interfaces using the Model Context Protocol.

Best for

Best for
Researchers and engineers who want to interact with PFC simulations through conversational AI agents

Use cases

• Run PFC DEM simulations via natural language commands
• Iterate on simulation parameters through conversation with an AI agent
• Automate batch simulation workflows using AI-driven orchestration

How to use

Install

uvx itasca-mcp

Tools exposed

• itasca_execute_code

Tested with

Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, toyoura-nagisa

Example client config

{\n  "mcpServers": {\n    "itasca-mcp": {\n      "command": "uvx",\n      "args": ["itasca-mcp"]\n    }\n  }\n}

Notes

An MCP server that connects AI agents to ITASCA PFC for running Discrete Element Method simulations through natural language. It enables agents to configure, execute, and retrieve simulation results via conversational interfaces using the Model Context Protocol.

63 stars on GitHub. Last updated 2026-05-29. Licensed MIT.

Use cases

• Run PFC DEM simulations via natural language commands
• Iterate on simulation parameters through conversation with an AI agent
• Automate batch simulation workflows using AI-driven orchestration

Pros

• Lowers the barrier to using complex DEM simulations by enabling conversational control
• Integrates seamlessly with AI agent frameworks via the standard MCP protocol
• Open source with an active community and regular updates

Cons

• Requires existing familiarity with ITASCA PFC software and its setup
• Limited to simulations that support the MCP server integration
• May introduce latency for large-scale or high-frequency simulation tasks

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.