Verdict MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 119 installs a week from pypi. Last commit 29 Aug 2026.
Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
We read the source, 3 d ago · rules ccca72095570
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(args, cwd=worktree, capture_output=True, text=True, check=False)
env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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-mcp -- uvx verdict-mcp
{
"mcpServers": {
"verdict-mcp": {
"args": [
"verdict-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.verdict-mcp]
command = "uvx"
args = ["verdict-mcp"]
{
"mcpServers": {
"verdict-mcp": {
"args": [
"verdict-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"verdict-mcp": {
"args": [
"verdict-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
VERDICT_PROJECT (Path to the project to verify (defaults to cwd)).
The author declared them in the registry entry; get the values from the project itself.
Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.
Sandboxed coding workers, verified: tests rerun fresh and must fail with the change reverted.
Test analytics for AI agents: test history, flaky tests, failure clusters, coverage.
Fail-closed, change-aware verification for AI coding agents with affected-test guidance.
AI browser tests from your coding agent: a verdict, failing steps, report, video and trace.
Fix production agent behavior with tested changes and a production verdict on every fix.
MCP server for AI-assisted coding with development history: git, tests, Copilot.
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
Answers built from our own checks of this server.