Benchmark Hygiene MCP Server
by sudo-ai-gitio.github.sudo-ai-git/mcp-benchmark-hygienev1.0.1
Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.
context tax
queued
security
queued
cold start
queued
freshness
Maintained42d ago
Install Benchmark Hygiene MCP server
Install in Claude Code
claude mcp add benchmark-hygiene -- uvx mcp-benchmark-hygieneInstall in Cursor
{
"mcpServers": {
"benchmark-hygiene": {
"command": "uvx",
"args": [
"mcp-benchmark-hygiene"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"benchmark-hygiene": {
"command": "uvx",
"args": [
"mcp-benchmark-hygiene"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"benchmark-hygiene": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-benchmark-hygiene"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"benchmark-hygiene": {
"command": "uvx",
"args": [
"mcp-benchmark-hygiene"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Maintained — last maintenance signal 42d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-08-28 · 42d ago · GitHub
Latest release
2026-08-28 · 43d ago · GitHub · v1.0.0
Package published
no data · npm/PyPI
Registry entry updated
2026-08-27 · 43d ago · official registry · v1.0.1
FAQ
›How do I install the Benchmark Hygiene MCP server in Claude Code?
Run: claude mcp add benchmark-hygiene -- uvx mcp-benchmark-hygiene. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Benchmark Hygiene require an API key?
No required environment variables are declared in its published metadata.
›Can I use Benchmark Hygiene as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Benchmark Hygiene in the official MCP registry?
Yes, as io.github.sudo-ai-git/mcp-benchmark-hygiene.
Alternatives to Benchmark Hygiene
Other ai & llm tools MCP servers.
FetchActiveWeb content fetching and conversion for efficient LLM usage
Claude FlowActiveAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
BrowserActiveA fast, lightweight MCP server that empowers LLMs with browser automation via Puppeteer’s structured accessibility data, featuring optional vision mode for complex visual understanding and flexible, cross-platform configuration.
PlaywrightActivePlaywright browser automation: interact with web pages through structured accessibility snapshots.
Serena AgentActiveA powerful toolkit for coding, providing semantic retrieval and editing capabilities.
TrycuaActiveMCP server for the Computer-Use Agent (CUA), allowing you to run CUA through Claude Desktop or other MCP clients.