Auditoria Skills runs on your own machine — the client starts it, so there is no endpoint to ping. 132 installs a week from pypi. Last commit 29 Jul 2026.
20 SKILLs de auditoría interna para agentes de IA según IIA, COSO, NIST, ISO, COBIT y ACFE.
Today is the operative word: we check Auditoria Skills 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 auditoria-skills -- uvx auditoria-skills-mcp
{
"mcpServers": {
"auditoria-skills": {
"args": [
"auditoria-skills-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.auditoria-skills]
command = "uvx"
args = ["auditoria-skills-mcp"]
{
"mcpServers": {
"auditoria-skills": {
"args": [
"auditoria-skills-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"auditoria-skills": {
"args": [
"auditoria-skills-mcp"
],
"command": "uvx"
}
}
}
Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.
Configura y entrena tus agentes de IA de WhatsApp e Instagram de TBit desde ChatGPT o Claude.
Dynamically load Claude Code skills into AI agents without copying files.
Emite CFDIs 4.0 y resuelve claves del SAT para agentes de IA (México), con permisos por API key.
Pre-deploy security auditor for AI agent code — the risks generic SAST misses.
29 live data skills for agents: email/DNS/domain intel, web audits, EVM reads. Free tier.
Let AI agents interact with serial devices — list ports, connect, send, and read.
Local-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.
Answers built from our own checks of this server.