Rigor MCP
A community-driven MCP server providing verified statistical inference for AI agents. It supports classical and non-parametric hypothesis testing, correlation, regression, effect sizes, power analysis, and multiple-comparisons correction. It includes a test-recommendation helper and batch pairwise-comparison tools, implemented using pure standard library statistics without external dependencies.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Perform hypothesis tests (t-tests, z-tests, chi-squared) for AI agents
- Calculate power and sample size for experimental designs
- Apply multiple-comparisons corrections to statistical results
- Use a test-recommendation helper to select appropriate statistical tests
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
rigor-mcp 0.5.0
{
"version": "0.5.0",
"transport": "stdio",
"identifier": "rigor-mcp",
"runtimeHint": "uvx",
"registryType": "pypi"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"rigor-mcp": {
"command": "uvx",
"args": [
"rigor-mcp==0.5.0"
]
}
}
}Cline
{
"mcpServers": {
"rigor-mcp": {
"command": "uvx",
"args": [
"rigor-mcp==0.5.0"
]
}
}
}VS Code
{
"servers": {
"rigor-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"rigor-mcp==0.5.0"
]
}
}
}Claude Desktop
{
"mcpServers": {
"rigor-mcp": {
"command": "uvx",
"args": [
"rigor-mcp==0.5.0"
]
}
}
}Let your agent find its tools
Find servers like Rigor MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.