Flakyguard runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 2 Nov 2026.
Flaky-test evidence tracker: per-test pass/fail history, flakiness rates, and a quarantine list.
Today is the operative word: we check Flakyguard 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 flakyguard -- npx -y @reneturcios/flakyguard
{
"mcpServers": {
"flakyguard": {
"command": "npx",
"args": [
"-y",
"@reneturcios/flakyguard"
]
}
}
}
[mcp_servers.flakyguard]
command = "npx"
args = ["-y", "@reneturcios/flakyguard"]
{
"mcpServers": {
"flakyguard": {
"command": "npx",
"args": [
"-y",
"@reneturcios/flakyguard"
]
}
}
}
{
"servers": {
"flakyguard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/flakyguard"
]
}
}
}
Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.
Known flaky tests, failing and slow CI, review flow, delivery and dependency risk from kept history.
Test analytics for AI agents: test history, flaky tests, failure clusters, coverage.
MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
BuildPulse CI test analytics for AI agents — flaky tests, CI failures, flakiness, and code coverage.
Fail reads in web and Electron test apps, inspect recovery, and compare before/after evidence.
Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.
Validate a startup idea with live web research: GO, PIVOT or NO_GO, with evidence and a first test.
Answers built from our own checks of this server.