Verdict QA runs on your own machine — the client starts it, so there is no endpoint to ping. 940 installs a week from pypi. Last commit 1 Nov 2026.
Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.
We read the source, 1 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
proc = subprocess.run(
"doas": ("uC", (), 0),
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
proc = subprocess.run(
expanded = os.path.join(cwd, expanded)
proc = subprocess.run(command, shell=True, cwd=str(scratch), env=env, capture_output=True,
env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Verdict QA and you get told the day something new turns up.
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 verdict -- uvx verdict-qa-mcp
{
"mcpServers": {
"verdict": {
"command": "uvx",
"args": [
"verdict-qa-mcp"
]
}
}
}
[mcp_servers.verdict]
command = "uvx"
args = ["verdict-qa-mcp"]
{
"mcpServers": {
"verdict": {
"command": "uvx",
"args": [
"verdict-qa-mcp"
]
}
}
}
{
"servers": {
"verdict": {
"type": "stdio",
"command": "uvx",
"args": [
"verdict-qa-mcp"
]
}
}
}
Flaky-test evidence tracker: per-test pass/fail history, flakiness rates, and a quarantine list.
Evidence-first browser QA with read-only MCP server for AI agent debugging.
MCP server for App Store Connect: releases, TestFlight, reviews, reports. Read-only by default.
MCP server for App Store Connect: releases, TestFlight, reviews, reports. Read-only by default.
Read-only MCP server: a coding agent reads test sessions recorded in QA Wrap. Local only.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Read-only web QA agent: scans a site in a real browser and returns evidence-backed findings
Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.
Answers built from our own checks of this server.