A security review for MCP servers, which are connected services that give an AI agent extra tools. It reads the servers configured in Hermes and reports their settings, credentials, sources, update times, and risks.

Use it to inspect tool filters, enabled status, timeouts, environment variables, transport types, package or repository sources, and update timestamps for every configured MCP server.

It helps reveal which tools and secrets each connected service can access and whether the configuration leaves unnecessary exposure.

audit-mcp — Skill for Claude Code and Codex by OnlyTerp: A security review for MCP servers, which are connected…

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.

agentmods

npx agentmods add skills/onlyterp/hermes-optimization-guide/audit-mcp

Any agent

npx skills add OnlyTerp/hermes-optimization-guide --skill audit-mcp

Clone the repo

git clone --depth 1 https://github.com/OnlyTerp/hermes-optimization-guide

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/onlyterp/hermes-optimization-guide/audit-mcp.svg)](https://agentmods.dev/skills/onlyterp/hermes-optimization-guide/audit-mcp)

Your own site

<a href="https://agentmods.dev/skills/onlyterp/hermes-optimization-guide/audit-mcp"><img src="https://agentmods.dev/badge/skills/onlyterp/hermes-optimization-guide/audit-mcp.svg" alt="Measured on agentmods" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,260 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.01260
Opus 5	$0.00010	$0.00630
Sonnet 5	$0.00004	$0.00252
Haiku 4.5	$0.00002	$0.00126

Measured 6d ago against content hash ce3803e7a11c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

audit-mcp 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 6d 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.

skills/security/audit-mcp/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

audit-mcp — MCP Server Security Audit

Walk every server declared in ~/.hermes/config.yaml under mcp_servers: and produce a structured report with risk flags.

Hermes has no per-server trust: levels or allow_sampling: knobs — the real controls are tool filtering (tools.include / tools.exclude), credential scoping (what you pass via env:), and operator review before install (Part 19, Layer 5). This audit checks exactly those.

Procedure

Read the config. Load ~/.hermes/config.yaml and extract the mcp_servers: block. If the block is empty or missing, report "No MCP servers configured" and exit.
For each server, collect:
- Server name and transport (stdio if command: present, http if url: present)
- enabled: flag and timeout:
- tools.include / tools.exclude — present? how many tools locked in vs exposed?
- env: entries — which credentials this server receives
- Source identifier: npm package (parse from args:), git URL, or HTTP origin
- Last-updated timestamp:
  - npm: npm view <pkg> time.modified
  - git: git -C <path> log -1 --format=%cI
  - http: attempt a HEAD and grab Last-Modified
Risk-flag each server:
- 🔴 HIGH: server ingests untrusted content (web scraping, email parsing, public RSS — tool names matching /scrape|fetch|email|rss|crawl/i) AND has an empty tools.include (= all tools exposed) or write-capable tools included.
- 🔴 HIGH: env: passes a broad credential (e.g. an unscoped GITHUB_PERSONAL_ACCESS_TOKEN) to a server that reads attacker-influenced text (the Comment-and-Control pattern).
- 🟡 MEDIUM: last updated > 90 days ago.
- 🟡 MEDIUM: empty tools.include on a server with > 10 tools exposed.
- 🟡 MEDIUM: referenced ${VAR} in env: is not set in ~/.hermes/.env (check key names only — never read values).
- 🟢 LOW: enabled: true on a server the logs show unused for 30+ days — dead attack surface.

Read the full file on GitHub · 92 lines

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.

6d ago First seen · 92 lines · 21 tokens per session scan A ce3803e7a11c

Subscribe to this mod's changes

audit-mcp is a skill published in the GitHub repository OnlyTerp/hermes-optimization-guide (629 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 1,260 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.

Building agents Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens