Verified statistical inference for AI agents -- classical and non-parametric hypothesis testing, correlation/regression, effect sizes, power/sample-size, multiple-comparisons correction, a test-recommendation helper, and a batch pairwise-comparison tool, as a CLI and an MCP server
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add rigor -- uvx rigor-mcp~/.codex/config.toml
[mcp_servers.rigor]
command = "uvx"
args = ["rigor-mcp"]
# codex mcp add rigor -- uvx rigor-mcp~/.cursor/mcp.json
{
"mcpServers": {
"rigor": {
"command": "uvx",
"args": [
"rigor-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"rigor": {
"type": "stdio",
"command": "uvx",
"args": [
"rigor-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"rigor": {
"command": "uvx",
"args": [
"rigor-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"rigor": {
"command": "uvx",
"args": [
"rigor-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"rigor": {
"command": "uvx",
"args": [
"rigor-mcp"
]
}
}
}