Sandbox
@yusong652/flac-mcp

MCP server for ITASCA FLAC

`flac-mcp` exposes FLAC documentation and execution tools over the Model Context Protocol. The server runs with `uvx flac-mcp`, and a small bridge started inside FLAC connects the live application to your agent.

39 stars4 forksPythonUpdated 2mo ago
Who it's for

Builders who want their agent to query FLAC docs, run simulations, and inspect task status from chat.

What it delivers

You can ask an agent to explore FLAC commands, execute code, and monitor long-running runs without leaving the conversation.

What it does

Documentation tools

Browse and search FLAC commands, Python API docs, and reference material without needing the bridge.

Execution tools

Use an interactive REPL, submit tasks, watch progress, interrupt running jobs, and review task history.

Multi-version FLAC support

Switch between FLAC 6.0, 7.0, and 9.0 docs with the `version` parameter.

Agent setup guide

A bootstrap guide in `docs/agentic/flac-mcp-bootstrap.md` walks an agent through configuration.

Bridge startup inside FLAC

`addon.py` starts the bridge from the FLAC IPython console or GUI.

How to get it

  1. 1Copy this to your AI agent and let it self-configure
    Fetch and follow this bootstrap guide end-to-end:
    https://raw.githubusercontent.com/yusong652/flac-mcp/main/docs/agentic/flac-mcp-bootstrap.md

README

flac-mcp

[!WARNING] flac-mcp is deprecated and frozen. It is superseded by itasca-mcp — a single multi-engine MCP server covering FLAC, PFC, 3DEC, MPoint, and MassFlow. Update your MCP client config from uvx flac-mcp to uvx itasca-mcp (select FLAC docs via the software parameter). No further releases are planned here.

flac-mcp — MCP Server for ITASCA FLAC

English | 简体中文

PyPI Downloads GitHub stars License: MIT Python 3.10+

flac3d>model new ;now, with LLM.

flac-mcp connects AI agents to ITASCA FLAC through the Model Context Protocol — browse documentation, run simulations, and execute code, all through natural conversation.

flac3d>model solve ;LLM solves.

Tools (10)

5 documentation tools — browse and search FLAC commands, Python API, and reference docs. No bridge required.

5 execution tools — interactive REPL, task submission, progress monitoring, interruption, and history. Requires bridge.

First-time Setup

Prerequisites

  • ITASCA FLAC 6.0, 7.0, or 9.0 installed
  • uv installed (for uvx)

Agentic Setup (Recommended)

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/flac-mcp/main/docs/agentic/flac-mcp-bootstrap.md

Manual Setup

1. Register the MCP server in your client config:

{
  "mcpServers": {
    "flac-mcp": {
      "command": "uvx",
      "args": ["flac-mcp"]
    }
  }
}

2. Start the bridge from inside FLAC:

Download addon.py, then use either of these two flows inside FLAC:

  • Copy the file contents into the FLAC IPython console and run them
  • Or download the file and execute it in FLAC GUI

Verify

Restart your AI agent (Claude Code, Codex CLI, Gemini CLI, etc.) and ask it to call flac_execute_code to verify the connection.

Daily Startup

Once first-time setup is done, each new FLAC session only needs the bridge re-started — run this in FLAC'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.

Features

  • Multi-version FLAC support - command docs for FLAC 6.0, 7.0, and 9.0 via the version parameter
  • Hierarchical documentation browsing - agents navigate the FLAC command tree to discover capabilities and boundaries, reducing hallucinated commands
  • Enhanced plot documentation - plot items reference docs supplementing the official documentation
  • Interactive REPL - rapid iteration before committing to full scripts; agents can quickly test and refine code
  • Task lifecycle management - submit long-running simulations, monitor progress, interrupt running tasks, and browse task history
  • Multi-client compatible - works with Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, toyoura-nagisa, and other MCP clients

Troubleshooting

See Troubleshooting in the bootstrap guide.

Development

See Developer Guide: Install and Run from Source.

Contributing

PRs and issues are welcome! See the Developer Guide to get started.

License

MIT - see LICENSE.

Files in the repo

Repository payload22 top-level entries
  • .github
  • docker
  • docs
  • scripts
  • src
  • tests
  • workspace
  • .dockerignore
  • .gitignore
  • .gitmodules
  • addon.py
  • AGENTS.md
  • CHANGELOG.md
  • CLAUDE.md
  • GEMINI.md
  • itasca-mcp-bridge
  • LICENSE
  • pyproject.toml
  • README.md
  • README.zh-CN.md
  • uv.lock
  • WARP.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k