MCP Benchmark Hygiene runs on your own machine — the client starts it, so there is no endpoint to ping. 827 installs a week from pypi. Last commit 28 Aug 2026.
Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.
We read the source, 13 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
r = subprocess.run(
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.
r = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 mcp-benchmark-hygiene -- uvx mcp-benchmark-hygiene
{
"mcpServers": {
"mcp-benchmark-hygiene": {
"args": [
"mcp-benchmark-hygiene"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-benchmark-hygiene]
command = "uvx"
args = ["mcp-benchmark-hygiene"]
{
"mcpServers": {
"mcp-benchmark-hygiene": {
"args": [
"mcp-benchmark-hygiene"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-benchmark-hygiene": {
"args": [
"mcp-benchmark-hygiene"
],
"command": "uvx"
}
}
}
Deterministic cross-branch conflict detection for AI coding agents
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
Deterministic market-state engine for trading agents — state, gate, coordinates, with receipts.
Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
Deterministic batch tools so LLM agents stop guessing dates and math.
Deterministic context selection for AI coding agents. Local memory that compounds across sessions.
Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.
Answers built from our own checks of this server.