ITASCA MCP Server logo

ITASCA MCP Server

Connects AI agents to ITASCA simulation engines for documentation lookup, code execution, task control, and plot-related workflows.

Install ITASCA MCP Server

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "itasca-mcp-server": {
      "command": "uvx",
      "args": [
        "itasca-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 10 tools correctly (Today).

Overview

ITASCA MCP Server MCP server connects AI agents to ITASCA’s PFC, FLAC3D, 3DEC, MPoint, and MassFlow software through MCP. It provides documentation browsing and search without a bridge, while execution features use a bridge running inside the selected ITASCA engine. Agents can execute code, submit and monitor simulations, interrupt tasks, inspect history, and work with live engine state. Use it when an agent needs to create, inspect, or troubleshoot geomechanics simulations through conversation.

Use cases

  • Search ITASCA command and Python API documentation
  • Build and run geomechanics simulation models
  • Monitor or interrupt long-running simulations
  • Inspect live model state during execution
  • Capture and review plot-related simulation output

Key features

  • Multi-engine documentation corpus
  • Command and Python API search
  • Interactive execution bridge
  • Simulation task monitoring
  • Task interruption and history
  • GUI activity visibility

Tools10

What ITASCA MCP Server lets your agent do. Expand a tool for its parameters.

Verified live~3.8k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

5/5 checks healthy over the last 28d

What it can do

From the 10 tools this server returned when we ran it.

Runs commands · 2Makes network requests · 7Read-only tools · 8
Network at startup2 connections
Files written at startup10

Observed 2026-10-24 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · itasca-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars220Stargazers on the source repository.
Last commit1d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed10Callable tools this server registers over MCP.

How ITASCA MCP Server works

What ITASCA MCP Server MCP server does

ITASCA MCP Server MCP server exposes ITASCA geomechanics software to MCP-compatible AI agents. Supported engines include PFC, FLAC, 3DEC, MPoint, and MassFlow, with documentation available across the versions listed by the project. The documentation corpus covers engine commands, Python APIs, reference material, and plot items.

The server is intended for workflows where an agent needs both guidance and access to a running simulation environment. For example, an agent can look up commands, build a model, run a biaxial test, inspect intermediate results, or help diagnose a command entered in the engine console.

How it works

The server provides ten tools divided into two groups. Five documentation tools let an agent browse and search the selected engine’s command tree, Python API, and reference documentation. These tools do not require a bridge. The selected product and version are supplied through tool parameters, allowing the agent to work with the relevant documentation set.

Five execution tools handle an interactive REPL, long-running task submission, progress checks, interruption, and task history. These operations require a bridge started from inside the ITASCA engine. With the bridge active, an agent can run code while a simulation continues, check model state without stopping the task, and use short REPL iterations before creating a larger script.

The bridge also forwards activity from the engine GUI to the agent on a later call. This includes IPython cells, console commands, opened or switched data files, plot changes, and files executed from the editor. An agent can therefore work alongside actions performed directly in the GUI.

Setup and configuration

An ITASCA engine must be installed locally: PFC, FLAC, 3DEC, MPoint, or MassFlow. The README recommends version 9.0 or later and also lists support for PFC 6.0 and 7.0, FLAC 7.0, and 3DEC 7.0. The setup uses Python 3.10 or newer and uv, including its uvx command.

Register the server with an MCP client using uvx itasca-mcp, either through the client’s MCP command or a configuration entry with command set to uvx and args set to ["itasca-mcp"]. The documented commands cover Claude Code, Codex, and Gemini CLI. After registration, download addon.py and run it from the engine’s IPython console or GUI. On later sessions, start the bridge with import itasca_mcp_bridge followed by itasca_mcp_bridge.start().

To verify the connection, restart the MCP client and ask it to call itasca_execute_code. The bridge checks PyPI for a newer bridge release when start() runs and upgrades itself before starting.

Tools and capabilities

ITASCA MCP Server MCP server supports these capability areas:

  • Search and navigate engine command, Python API, and reference documentation.
  • Select documentation by software and version.
  • Execute code through an interactive REPL.
  • Submit simulations as tasks and monitor their progress.
  • Interrupt running tasks and review task history.
  • Work with live simulations while they remain active.
  • Receive selected activity from the ITASCA GUI, including plot and data-file actions.

Limitations and notes

Documentation lookup works without the bridge, but execution tools do not. A compatible ITASCA engine installation is therefore required for simulation control and code execution. The bridge must be started again for each new engine session. The repository describes support for specific engine versions rather than every possible ITASCA release, so the selected software and version should match the installed environment.

The project documents compatibility with Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, toyoura-nagisa, and other MCP clients. Client configuration details may differ outside the explicitly documented setup commands.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about ITASCA MCP Server

ITASCA MCP Server is an MCP server that connects AI agents to ITASCA’s PFC, FLAC, 3DEC, MPoint, and MassFlow software. Its main tools support documentation search, interactive code execution, simulation task submission, progress monitoring, interruption, and task history; execution requires a bridge inside the engine.

Install `uv`, register `uvx itasca-mcp` with your MCP client, and install an ITASCA engine. Then run the provided bridge setup inside the engine using `addon.py`; later sessions require starting `itasca_mcp_bridge` again.

Yes, Claude Code is explicitly documented as a supported client. Register it with `claude mcp add itasca-mcp -- uvx itasca-mcp`, then start the bridge inside the ITASCA engine before using execution tools.

Yes, execution tools require a bridge running inside the selected ITASCA engine. Documentation browsing and search work without the bridge, but REPL execution, task submission, progress monitoring, interruption, and history depend on it.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewITASCA MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/itasca-mcp-server?style=directory)](https://allmcps.com/mcp/itasca-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/itasca-mcp-server"><img src="https://allmcps.com/api/badge/itasca-mcp-server?style=directory" alt="ITASCA MCP Server on AllMCPs" /></a>