Backtest Auditor runs on your own machine — the client starts it, so there is no endpoint to ping. 830 installs a week from pypi.
Automated red-team checks for trading backtests: lookahead lint, Deflated Sharpe, costs. Local.
Today is the operative word: we check Backtest Auditor every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 backtest-auditor -- uvx backtest-auditor
{
"mcpServers": {
"backtest-auditor": {
"command": "uvx",
"args": [
"backtest-auditor"
]
}
}
}
[mcp_servers.backtest-auditor]
command = "uvx"
args = ["backtest-auditor"]
{
"mcpServers": {
"backtest-auditor": {
"command": "uvx",
"args": [
"backtest-auditor"
]
}
}
}
{
"servers": {
"backtest-auditor": {
"type": "stdio",
"command": "uvx",
"args": [
"backtest-auditor"
]
}
}
}
Static analyzer flagging lookahead bias & data leakage in ML/trading code before backtest.
Tech stack, WHOIS, DNS, SSL, hosting and SEO checks for lists of domains.
kube-linter audit for Kubernetes manifests — 63 checks: security, availability, RBAC, network.
Offline PineScript v6 → C++ backtests at deterministic TradingView parity, run locally via MCP.
A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
PlatformIO for AI agents: build, flash, serial monitor, tests, crash decoding, size reports.
Shared local memory for AI coding tools that stays true to your code.
Answers built from our own checks of this server.