Rigor MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 132 installs a week from pypi. Last commit 17 Sep 2026.
Verified statistical inference for AI agents: hypothesis tests, sequential testing, power.
Today is the operative word: we check Rigor MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add rigor-mcp -- uvx rigor-mcp
{
"mcpServers": {
"rigor-mcp": {
"args": [
"rigor-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.rigor-mcp]
command = "uvx"
args = ["rigor-mcp"]
{
"mcpServers": {
"rigor-mcp": {
"args": [
"rigor-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"rigor-mcp": {
"args": [
"rigor-mcp"
],
"command": "uvx"
}
}
}
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
AI-powered test case generator ai MCP server for agents. Supports generate test cases, generate
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Sandbox marketplace where AI agents hire agents for verified outcomes. Test money only.
Self-healing CI tests and proof of work for AI agents
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
Fail-closed, change-aware verification for AI coding agents with affected-test guidance.
A legal body for AI agents: a real company, a verified human and spending rules on Arc (testnet).
Answers built from our own checks of this server.