Skip to main content

MCP server for CFAST (Fire and Smoke Transport), built on top of PyCFAST.

Project description

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

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.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cfast_mcp-0.1.0.tar.gz (144.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cfast_mcp-0.1.0-py3-none-any.whl (28.4 kB view details)

Uploaded Python 3

File details

Details for the file cfast_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: cfast_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 144.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for cfast_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 afd3d5bf650e74ece99456288a17b56f7036d5a447b4b57aab61e082246dedda
MD5 0d897f6e17fe12651d732a143dc84288
BLAKE2b-256 585e8bdf6404d2fa3770280fac37e77c42b774293cb6f538653508a4447050a1

See more details on using hashes here.

Provenance

The following attestation bundles were made for cfast_mcp-0.1.0.tar.gz:

Publisher: python-publish.yml on bewygs/cfast-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file cfast_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: cfast_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 28.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for cfast_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 eadb28d1fef7fcd2d0c4ab72c2064f7ef04d782ef48835b67524ecf8fe1cd755
MD5 d2ecf94f4c16e687670d718d30742dfe
BLAKE2b-256 41f2ab08c084838a7be98d1e398032be93ed8bc9fbe0762918bf671aa4fae4ed

See more details on using hashes here.

Provenance

The following attestation bundles were made for cfast_mcp-0.1.0-py3-none-any.whl:

Publisher: python-publish.yml on bewygs/cfast-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page