MQ-Sentinel runs on your own machine — the client starts it, so there is no endpoint to ping. 150 installs a week from pypi. Last commit 18 Oct 2026.
Read-only IBM MQ diagnostics for AI agents. Cited root cause, never destructive.
We read the source, 5 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( # noqa: S603 — argv list, no shell, allowlisted
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( # noqa: S603 — argv list, no shell, allowlisted
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 MQ-Sentinel 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 mq-sentinel -- uvx mq-sentinel
{
"mcpServers": {
"mq-sentinel": {
"command": "uvx",
"args": [
"mq-sentinel"
]
}
}
}
[mcp_servers.mq-sentinel]
command = "uvx"
args = ["mq-sentinel"]
{
"mcpServers": {
"mq-sentinel": {
"command": "uvx",
"args": [
"mq-sentinel"
]
}
}
}
{
"servers": {
"mq-sentinel": {
"type": "stdio",
"command": "uvx",
"args": [
"mq-sentinel"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MQS_AUTH_DISABLE_AUTH_FOR_LOCAL_DEV (Set true for local demo only. Refused when environment=prod), MQS_SERVER_ENVIRONMENT (dev | staging | prod — used in audit and RBAC).
Read-only npm dependency diagnostics for AI coding agents.
Read-only MCP diagnostics server for RavenDB.
SQL Server monitoring and diagnostics for AI agents using Extended Events. No ODBC drivers required.
Read-only SQL Server diagnostics for LLM agents: Query Store, waits, plans, indexes
ClickHouse query & management for AI agents — SQL-classified read/write/destructive gating.
Industrial AI-readiness diagnostics, UNS design, and UNS agents for MCP clients.
Read-only Exeris context for AI agents: ADRs, SDK contract, build output, kernel diagnostics.
Read-only local zoxide diagnostics for MCP clients.
Answers built from our own checks of this server.