Bridges Claude and other AI agents directly to ITASCA PFC, the discrete element method simulation software. Exposes 10 tools split between documentation browsing (commands, Python API, reference docs across PFC 6.0, 7.0, and 9.0) and execution control (REPL, task submission, progress monitoring, interrupts, history). Setup requires a Python bridge running inside PFC's IPython console to handle the execution side, while doc tools work standalone. Useful if you're running particle simulations and want an agent that can navigate PFC's command hierarchy, test code interactively, and monitor long running DEM models without leaving the conversation.
itasca>model new ;now, with LLM.
itasca-mcp connects AI agents to ITASCA's numerical modeling software — PFC, FLAC, 3DEC, MPoint, and MassFlow — through the Model Context Protocol. Browse documentation, run simulations, and execute code, all through natural conversation. Pick the engine with the software parameter.
itasca>model solve ;LLM solves.

5 documentation tools — browse and search the selected engine's commands, Python API, and reference docs (software parameter). No bridge required.
5 execution tools — interactive REPL, task submission, progress monitoring, interruption, and history. Requires bridge.
uvx)Copy this to your AI agent and let it self-configure:
Fetch and follow this bootstrap guide end-to-end:
https://raw.githubusercontent.com/yusong652/itasca-mcp/main/docs/agentic/itasca-mcp-bootstrap.md
1. Register the MCP server with your agent.
Most agents register it with a single command:
# Claude Code
claude mcp add itasca-mcp -- uvx itasca-mcp
# Codex / Codex-cli
codex mcp add itasca-mcp -- uvx itasca-mcp
# Gemini CLI
gemini mcp add itasca-mcp uvx itasca-mcp
Or fill in the MCP config file manually:
{
"mcpServers": {
"itasca-mcp": {
"command": "uvx",
"args": ["itasca-mcp"]
}
}
}
2. Start the bridge from inside the ITASCA engine:
Download addon.py, then use either of these two flows inside the engine GUI (PFC, FLAC, 3DEC, ...):
Restart your AI agent (Claude Code, Codex CLI, Gemini CLI, etc.) and ask it to call itasca_execute_code to verify the connection.
Once first-time setup is done, each new engine session only needs the bridge re-started — run this in the engine's IPython console and you're back online:
import itasca_mcp_bridge
itasca_mcp_bridge.start()
start() checks PyPI for a newer bridge release and self-upgrades before starting. The MCP client config persists.
software parameterversion parameterSee Troubleshooting in the bootstrap guide.
See Developer Guide: Install and Run from Source.
PRs and issues are welcome! See the Developer Guide to get started.
MIT - see LICENSE.