mcpbeat Sign in

MCP Benchmark Hygiene MCP Server

local only

MCP Benchmark Hygiene runs on your own machine — the client starts it, so there is no endpoint to ping. 91 installs a week from pypi. Last commit 28 Aug 2026.

Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.

Installs per day peak 26 · avg 13 · +3% w/w
a month agotoday
91
Installs / week
pypi · mcp-benchmark-hygiene
0
Stars
0 open issues
28 Aug 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 5 h ago · rules ccca72095570

A tool parameter reaches a dangerous call

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.

A tool parameter reaches a dangerous call inspect_workspace.path → mcp_server.py:103
        r = subprocess.run(
Capabilities

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.

A tool parameter here reaches a dangerous call

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.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add mcp-benchmark-hygiene -- uvx mcp-benchmark-hygiene
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp-benchmark-hygiene": {
      "args": [
        "mcp-benchmark-hygiene"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcp-benchmark-hygiene]
command = "uvx"
args = ["mcp-benchmark-hygiene"]
.cursor/mcp.json
{
  "mcpServers": {
    "mcp-benchmark-hygiene": {
      "args": [
        "mcp-benchmark-hygiene"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mcp-benchmark-hygiene": {
      "args": [
        "mcp-benchmark-hygiene"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to MCP Benchmark Hygiene

same job, measured the same way
Rosentic
by rosentic

Deterministic cross-branch conflict detection for AI coding agents

174 installs/wk local only
MCP Secret Scrub
by sudo-ai-git

Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.

96 installs/wk local only
Decker
by gigshow

Deterministic market-state engine for trading agents — state, gate, coordinates, with receipts.

12 tools answering
Orchestraguard
by harsh-chandak

Stop a team of coding agents contradicting each other. Deterministic, no model call.

local only
Boot Doctor MCP
by pamela-0

Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.

105 installs/wk local only
Veto — SQL Safety & Cost Oracle
by vetosql

Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.

3 tools answering
gnomon
by lihtness

Deterministic batch tools so LLM agents stop guessing dates and math.

129 installs/wk local only
Codeledger
by codeledgerecf

Deterministic context selection for AI coding agents. Local memory that compounds across sessions.

1 397 installs/wk local only

MCP Benchmark Hygiene — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP Benchmark Hygiene?
MCP Benchmark Hygiene runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mcp-benchmark-hygiene was installed 91 times last week.
How do I connect MCP Benchmark Hygiene?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mcp-benchmark-hygiene straight from pypi; nothing to host, nothing to sign up for.
How many people use MCP Benchmark Hygiene?
The pypi package mcp-benchmark-hygiene was installed 91 times in the last week. Week over week that is +3%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is MCP Benchmark Hygiene open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.