agentmods.dev

auditoria-skills

auditoria-skills is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from marcelinero/auditoria-skills-mcp. Its token cost is not measured, scanned A, original, CC-BY-SA-4.0.

A local server containing 20 internal-audit skills based on standards from organisations and frameworks such as IIA, COSO, NIST, ISO and IFRS. MCP is a way for an AI agent to use external tools.

In plain words
What is it for?
Tasks involving internal audit, controls, risk, information security, financial reporting or compliance.
Why use it?
It gives an agent structured audit guidance grounded in recognised standards, reducing the need to provide that material manually.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 0repo 1mo ago A scan tokens not measured CC-BY-SA-4.0

Good fit Tasks involving internal audit, controls, risk, information security, financial reporting or compliance.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/marcelinero/auditoria-skills-mcp/auditoria-skills
View source ↗ marcelinero/auditoria-skills-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/marcelinero/auditoria-skills-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for auditoria-skills

README.md
[![agentmods](https://agentmods.dev/badge/mcp/marcelinero/auditoria-skills-mcp/auditoria-skills/github.svg)](https://agentmods.dev/mcp/marcelinero/auditoria-skills-mcp/auditoria-skills)
Your own site
<a href="https://agentmods.dev/mcp/marcelinero/auditoria-skills-mcp/auditoria-skills"><img src="https://agentmods.dev/badge/mcp/marcelinero/auditoria-skills-mcp/auditoria-skills/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auditoria-skills

Your own site · 80×15
<a href="https://agentmods.dev/mcp/marcelinero/auditoria-skills-mcp/auditoria-skills"><img src="https://agentmods.dev/badge/mcp/marcelinero/auditoria-skills-mcp/auditoria-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

auditoria-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 9 lines

The source is not reproduced here

Licensed CC-BY-SA-4.0

The repository is licensed CC-BY-SA-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 9 lines scan A afed5354295f

Subscribe to this mod's changes

auditoria-skills is an MCP server published in the GitHub repository marcelinero/auditoria-skills-mcp (0 stars, last pushed 1mo ago), licensed CC-BY-SA-4.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Legal and compliance
Related

Other mcp servers, from other repositories

mcp-onfido

MCP server for Onfido — global identity verification + KYC: applicants, documents, checks, workflows. Runs locally from the @codespar/mcp-onfido npm package. Needs 2 environment variables to run.

codespar/mcp-dev-latam · not measured

smokeball-mcp

MCP server for Smokeball API — full coverage for law firm practice management. Runs locally from the smokeball-mcp Python package.

RosenAdvertising/smokeball-mcp · not measured

kbv-server

Real-time Korean business verification via the National Tax Service (NTS). Free during pilot. Remote server at kbv-server-f7vfitmlkq-du.a.run.app.

Wonderfulian/kbv-server · not measured

eu-ai-act

MCP server "eu-ai-act", hosted remotely at mcp.lexbeam.com, as configured in lexbeam-software/eu-ai-governance-plugin.

lexbeam-software/eu-ai-governance-plugin · not measured

acquis

Verified EU law: verbatim, signed provisions with EUR-Lex links. Read-only, not legal advice. Remote server at api.acquislaw.com.

capybarist/acquis-mcp · not measured

pref_sp_ribeirao_preto_cnd-mcp

Prefeitura SP Ribeirão Preto: Clearance Certificate (Debts), official-source lookup. Platform-hosted. Remote server at api.mcp.ai.

mcp-dir/pref_sp_ribeirao_preto_cnd-mcp · not measured