Skip to main content
Glama
bewygs

CFAST MCP

by bewygs

CFAST MCP

An MCP server that lets an LLM build, inspect, run, and analyze CFAST (Consolidated Fire and Smoke Transport, NIST) fire models step by step, via PyCFAST.

It exposes tools to add/update compartments, materials, vents, fires, devices, and surface connections, then run the simulation and read results as bounded summaries.

Installation

Requires Python 3.10+ and CFAST 7.7.0+.

CFAST

Download and install CFAST from the NIST CFAST website or the CFAST GitHub repository, and ensure cfast is on your PATH. If it's installed elsewhere, set the CFAST environment variable to the executable path:

export CFAST="/path/to/your/cfast/executable"

Server

pip install cfast-mcp

Related MCP server: BULC Building Designer

Usage

Add the server to your MCP client configuration:

{
  "mcpServers": {
    "cfast": {
      "command": "cfast-mcp",
      "env": { "CFAST": "/path/to/your/cfast/executable" }
    }
  }
}

Or run it directly:

cfast-mcp

Development

git clone https://github.com/bewygs/cfast-mcp.git
cd cfast-mcp
uv sync --extra dev          # install dev dependencies
uv run pytest                # run tests
uv run ruff check --fix .    # lint
uv run ruff format .         # format
uv run mypy src/              # type-check

See CLAUDE.md for architecture and contribution details.

A
license - permissive license
-
quality - not tested
-
maintenance - not tested

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bewygs/cfast-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server