MCP server

Benchmark Hygiene

io.github.sudo-ai-git/mcp-benchmark-hygiene

Checked 25 Oct 2026, 21:11 UTC · Still published on its registry; checked against OSV.dev; never run by us

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

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Runs on your computer

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code

Last checked

25 Oct 2026, 21:11 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.

Claude Code

claude mcp add mcp-benchmark-hygiene -- uvx mcp-benchmark-hygiene@1.0.1

Claude Desktop

{"mcpServers":{"mcp-benchmark-hygiene":{"command":"uvx","args":["mcp-benchmark-hygiene@1.0.1"]}}}

Codex (config.toml)

[mcp_servers.mcp-benchmark-hygiene]
command = "uvx"
args = ["mcp-benchmark-hygiene@1.0.1"]

Gemini CLI

{"mcpServers":{"mcp-benchmark-hygiene":{"command":"uvx","args":["mcp-benchmark-hygiene@1.0.1"]}}}

Cursor

{"mcpServers":{"mcp-benchmark-hygiene":{"command":"uvx","args":["mcp-benchmark-hygiene@1.0.1"]}}}

VS Code

{"servers":{"mcp-benchmark-hygiene":{"type":"stdio","command":"uvx","args":["mcp-benchmark-hygiene@1.0.1"]}}}

Runs on your computer with your permissions: check the package and its source before installing.

Browse

• GitHub tools
• GitHub and code hosting
• Calling other AI models

Related MCP servers

• The Stall
  277 pay-per-call MCP tools: YouTube keyword research, stocks, crypto, DeFi, options, macro.
• Stratalize Crypto & DeFi
  Retired. Use com.stratalize/stratalize.
• Sipflow
  SIP/VoIP/telecom grounding for AI agents: vendor docs, RFCs, STIR/SHAKEN, traces, configs.
• Sigistry Plugin Catalog (formerly Claude Registry)
  Renamed: prefer com.sigistry/plugin-catalog. This legacy endpoint keeps working.
• Axis Iliad - Codebase Intelligence For Agentic Commerce
  Codebase intelligence for agents: 152 structured artifacts across 21 programs, one call.
• Entity Enricher
  Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
• Hugging Face
  Connect to Hugging Face Hub and thousands of Gradio AI Applications
• Affine.Earth Math Court
  No-float UUM-8D Math Court. Integer courts and certified MCP. Floats refused.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.sudo-ai-git/mcp-benchmark-hygiene.svg)](https://aptlynx.net/servers/io.github.sudo-ai-git/mcp-benchmark-hygiene)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents