{ "markdown": "

\n \"itasca-mcp\"\n

\n\n# itasca-mcp\n\n[English](https://github.com/yusong652/itasca-mcp/blob/main/README.md) | [简体中文](https://github.com/yusong652/itasca-mcp/blob/main/README.zh-CN.md)\n\n[![CI](https://github.com/yusong652/itasca-mcp/actions/workflows/test.yml/badge.svg)](https://github.com/yusong652/itasca-mcp/actions/workflows/test.yml)\n[![PyPI](https://img.shields.io/pypi/v/itasca-mcp)](https://pypi.org/project/itasca-mcp/)\n[![Downloads](https://static.pepy.tech/badge/itasca-mcp)](https://pepy.tech/project/itasca-mcp)\n[![GitHub stars](https://img.shields.io/github/stars/yusong652/itasca-mcp)](https://github.com/yusong652/itasca-mcp/stargazers)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue)](https://www.python.org/)\n\n`itasca>model new ;now, with LLM.`\n\n**itasca-mcp** connects AI agents to [ITASCA](https://www.itascacg.com/)'s geomechanics simulation software — PFC, FLAC, 3DEC, MPoint, and MassFlow — through the [Model Context Protocol](https://modelcontextprotocol.io/). Browse documentation, run simulations, and execute code, all through natural conversation.\n\n`itasca>model solve ;LLM solves.`\n\n![itasca-mcp demo](https://raw.githubusercontent.com/yusong652/itasca-mcp/assets/itasca-mcp.gif)\n\n## Tools (10)\n\n**5 documentation tools** — browse and search the selected engine's commands, Python API, and reference docs. No bridge required.\n\n**5 execution tools** — interactive REPL, task submission, progress monitoring, interruption, and history. Requires bridge.\n\n## Example Prompts\n\n- *\"Run a biaxial compression test on a dense specimen and plot the stress–strain curve\"*\n- *\"Build a slope model in FLAC3D and find the factor of safety\"*\n- *\"Model a tunnel excavation in jointed rock with 3DEC and check block displacements around the opening\"*\n- *\"Simulate a landslide runout with MPoint and report the final deposit profile\"*\n- *\"The simulation is still running — check the current unbalanced force without stopping it\"*\n- *\"What's different about the `zone` commands between FLAC 7.0 and 9.0?\"*\n\n## First-time Setup\n\n### Prerequisites\n\n- **An ITASCA engine installed** — PFC, FLAC, 3DEC, MPoint, or MassFlow. 9.0+ recommended; PFC 6.0 / 7.0, FLAC 7.0, and 3DEC 7.0 are also supported.\n- **[uv](https://docs.astral.sh/uv/getting-started/installation/)** installed (for `uvx`)\n- **An AI agent** — Claude Code, Codex CLI, Gemini CLI, or any MCP-capable client\n\n### Agentic Setup (Recommended)\n\nCopy this to your AI agent and let it self-configure:\n\n```text\nFetch and follow this bootstrap guide end-to-end:\nhttps://raw.githubusercontent.com/yusong652/itasca-mcp/main/docs/agentic/itasca-mcp-bootstrap.md\n```\n\n### Manual Setup\n\n**1. Register the MCP server** with your agent.\n\nMost agents register it with a single command:\n\n```bash\n# Claude Code\nclaude mcp add itasca-mcp -- uvx itasca-mcp\n\n# Codex / Codex-cli\ncodex mcp add itasca-mcp -- uvx itasca-mcp\n\n# Gemini CLI\ngemini mcp add itasca-mcp uvx itasca-mcp\n```\n\nOr fill in the MCP config file manually:\n\n```json\n{\n \"mcpServers\": {\n \"itasca-mcp\": {\n \"command\": \"uvx\",\n \"args\": [\"itasca-mcp\"]\n }\n }\n}\n```\n\n**2. Start the bridge from inside the ITASCA engine:**\n\nDownload [`addon.py`](addon.py), then use either of these two flows inside the engine GUI (PFC, FLAC, 3DEC, ...):\n\n- Copy the file contents into the engine's IPython console and run them\n- Or download the file and execute it in the engine GUI\n\n\"addon.py\n\n### Verify\n\nRestart your AI agent and ask it to call `itasca_execute_code` to verify the connection.\n\n## Daily Startup\n\nOnce 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:\n\n```python\nimport itasca_mcp_bridge\nitasca_mcp_bridge.start()\n```\n\n`start()` checks PyPI for a newer bridge release and self-upgrades before starting. The MCP client config persists.\n\n## Features\n\n- **Multi-engine corpus** - command, Python API, and reference docs for PFC, FLAC, 3DEC, MPoint, and MassFlow, selected via the required `software` parameter\n- **Multi-version support** - command docs across engine versions (PFC: 6.0/7.0/9.0, FLAC: 7.0/9.0, 3DEC: 7.0/9.0) via the `version` parameter\n- **Hierarchical documentation browsing** - agents navigate the engine command tree to discover capabilities and boundaries, reducing hallucinated commands\n- **Enhanced plot documentation** - plot items reference docs supplementing the official documentation\n- **Live REPL alongside running tasks** - execute code while a simulation is running: check model state and intermediate results without stopping the task; also useful for quick iteration before writing a full script\n- **Task lifecycle management** - submit long-running simulations, monitor progress, interrupt running tasks, and browse task history\n- **Multi-client compatible** - works with Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, toyoura-nagisa, and other MCP clients\n\n## Troubleshooting\n\nSee [Troubleshooting](docs/agentic/itasca-mcp-bootstrap.md#troubleshooting) in the bootstrap guide.\n\n## Development\n\nSee [Developer Guide: Install and Run from Source](docs/development/source-install.md).\n\n\n \"itasca-mcp\n\n\n## Contributing\n\nPRs and issues are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for where changes land and how the\ndocumentation corpus is structured, and the [Developer Guide](docs/development/source-install.md) for the\nsource install.\n\n## License\n\nMIT - see [LICENSE](LICENSE).\n\n\n", "bytes": 6011, "sha": "53c1e7e62167e975adc519120e59ea57240051376532576489210ecf8b6b54fc", "repo_slug": "yusong652/itasca-mcp", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_yusong652_itasca_mcp_94ceac6f/readme" }