Reproducible scientific modeling engine and agent skill pack: versioned Model IR with mandatory units, dimensional and numerical validation, calibration, uncertainty analysis, and portable export (SBML, CellML, Modelica) via CLI, REST and MCP. Install: pip install axiomize.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add axiomize -- uvx axiomize~/.codex/config.toml
[mcp_servers.axiomize]
command = "uvx"
args = ["axiomize"]
# codex mcp add axiomize -- uvx axiomize~/.cursor/mcp.json
{
"mcpServers": {
"axiomize": {
"command": "uvx",
"args": [
"axiomize"
]
}
}
}.vscode/mcp.json
{
"servers": {
"axiomize": {
"type": "stdio",
"command": "uvx",
"args": [
"axiomize"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"axiomize": {
"command": "uvx",
"args": [
"axiomize"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"axiomize": {
"command": "uvx",
"args": [
"axiomize"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"axiomize": {
"command": "uvx",
"args": [
"axiomize"
]
}
}
}