PFC
MCP server that gives AI agents full access to ITASCA PFC - browse documentation, run simulations, capture plots, all through natural conversation. Built on the Model Context Protocol, pfc-mcp turns any MCP-compatible AI client (Claude Code, Codex CL
What is PFC?
PFC is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that gives ai agents full access to itasca pfc - browse documentation, run simulations, capture plots, all through natural conversation. built on the model context protocol, pfc-mcp turns a...
MCP server that gives AI agents full access to ITASCA PFC - browse documentation, run simulations, capture plots, all through natural conversation. Built on the Model Context Protocol, pfc-mcp turns any MCP-compatible AI client (Claude Code, Codex CL
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server that gives AI agents full access to ITASCA PFC -
Use Cases
Maintainer
Works with
Installation
PIP
pip install pfc-mcpManual Installation
pip install pfc-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use PFC
pfc-mcp is a Python MCP server that gives AI agents full programmatic access to ITASCA PFC, the discrete element method simulation software widely used in geomechanics research. Through a bridge running inside PFC's IPython console, AI clients can browse PFC command and Python API documentation, submit and monitor simulations, interact with a live REPL, and retrieve plot outputs — all through natural conversation. Researchers and engineers use it to accelerate DEM simulation workflows without leaving their AI coding environment.
Prerequisites
- ITASCA PFC version 6.0, 7.0, or 9.0 installed on your machine
- Python 3.10+ and the uv package manager (pip install uv or curl-based installer)
- The addon.py bridge file downloaded from the pfc-mcp GitHub repository
- An MCP-compatible client such as Claude Code, Claude Desktop, or Gemini CLI
Install pfc-mcp via pip or uvx
Install the pfc-mcp package from PyPI using pip or uvx. uvx is recommended for isolated execution without polluting global packages.
# With pip
pip install pfc-mcp
# With uvx (no permanent install needed)
uvx pfc-mcpDownload the bridge file into your PFC project folder
Clone or download addon.py from the repository and place it where your PFC project files are stored. This script starts the bridge between PFC and the MCP server.
git clone https://github.com/yusong652/pfc-mcp
cp pfc-mcp/addon.py /path/to/your/pfc-project/Start the itasca_mcp_bridge inside PFC
Open ITASCA PFC and launch its embedded IPython console. Import and start the bridge module so it can receive instructions from the MCP server.
import itasca_mcp_bridge
itasca_mcp_bridge.start()Register the server with your MCP client
Add pfc-mcp to your MCP client configuration. For Claude Code, use the .mcp.json file in your project root or the claude_desktop_config.json for Claude Desktop.
{
"mcpServers": {
"pfc-mcp": {
"command": "uvx",
"args": ["pfc-mcp"]
}
}
}Verify the connection and browse documentation
Restart your MCP client and ask it to list available PFC commands or browse the PFC documentation. The tools panel should show PFC documentation and execution tools.
PFC Examples
Client configuration
Minimal claude_desktop_config.json entry for pfc-mcp using uvx.
{
"mcpServers": {
"pfc-mcp": {
"command": "uvx",
"args": ["pfc-mcp"]
}
}
}Prompts to try
Example prompts that leverage pfc-mcp's documentation and simulation execution tools.
- "Browse the PFC command reference for the 'ball' keyword"
- "Show me the Python API documentation for the itasca.ball module"
- "Submit a PFC simulation using the script at /project/assembly.p3dat and monitor its progress"
- "Open an interactive REPL session in PFC and create 100 balls with radius 0.5"
- "Capture the current plot from the PFC model and save it as a PNG"Troubleshooting PFC
Bridge fails to connect — 'itasca_mcp_bridge module not found'
Make sure addon.py is present in your PFC working directory and that you ran 'pip install pfc-mcp' in the Python environment PFC uses before importing the bridge.
PFC version mismatch errors when submitting tasks
pfc-mcp supports PFC 6.0, 7.0, and 9.0. Pass the correct version parameter when calling task submission tools and ensure the installed pfc-mcp matches your PFC version.
uvx not found in PATH
Install uv via 'pip install uv' or the official installer at https://docs.astral.sh/uv/ and restart your terminal before running uvx pfc-mcp.
Frequently Asked Questions about PFC
What is PFC?
PFC is a Model Context Protocol (MCP) server that mcp server that gives ai agents full access to itasca pfc - browse documentation, run simulations, capture plots, all through natural conversation. built on the model context protocol, pfc-mcp turns any mcp-compatible ai client (claude code, codex cl It connects AI assistants to external tools and data sources through a standardized interface.
How do I install PFC?
Install via pip with: pip install pfc-mcp. Then configure your AI client to connect to this MCP server.
Which AI clients work with PFC?
PFC works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is PFC free to use?
Yes, PFC is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
PFC Alternatives — Similar Developer Tools Servers
Looking for alternatives to PFC? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up PFC in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use PFC?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.