HelloGrowthCRMwebsite_MCP: Skill for Claude Code

.claude/skills/mcp-server-audit/SKILL.md

mcp-server-audit is a skill for Claude Code from MeruLocal/HelloGrowthCRMwebsite_MCP. It costs 110 tokens per session (2,024 once invoked), scanned A, original, MIT.

A skill for checking an MCP server end to end. MCP is a standard way for AI applications to connect to tools and data, and this check covers its protocol, tool definitions, sessions, errors, discovery, write safety, and the truth of its content.

In plain words
What is it for?
Use it to audit a live or local MCP server and record failures, warnings, and passing checks.
Why use it?
It finds compatibility problems, unsafe write operations, and inaccurate information that a basic scanner may miss.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is MeruLocal/HelloGrowthCRMwebsite_MCP's own configuration. It tells Claude Code how to work on HelloGrowthCRMwebsite_MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything HelloGrowthCRMwebsite_MCP configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/audit-live-mcp.mjs # production.

Reuse

Borrowing it

Nothing to install: this file belongs to MeruLocal/HelloGrowthCRMwebsite_MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MeruLocal/HelloGrowthCRMwebsite_MCP/main/.claude/skills/mcp-server-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MeruLocal/HelloGrowthCRMwebsite_MCP

Made for: Claude Code.

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 mcp-server-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/merulocal/hellogrowthcrmwebsite_mcp/mcp-server-audit/github.svg)](https://agentmods.dev/skills/merulocal/hellogrowthcrmwebsite_mcp/mcp-server-audit)
Your own site
<a href="https://agentmods.dev/skills/merulocal/hellogrowthcrmwebsite_mcp/mcp-server-audit"><img src="https://agentmods.dev/badge/skills/merulocal/hellogrowthcrmwebsite_mcp/mcp-server-audit/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 mcp-server-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/merulocal/hellogrowthcrmwebsite_mcp/mcp-server-audit"><img src="https://agentmods.dev/badge/skills/merulocal/hellogrowthcrmwebsite_mcp/mcp-server-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.02024
Opus 5 $0.00055 $0.01012
Sonnet 5 $0.00022 $0.00405
Haiku 4.5 $0.00011 $0.00202

Measured 8d ago against content hash fbb0a7282df2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-server-audit scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Do the URLs resolve?** `curl -o /dev/null -w "%{http_code}"` every URL the
.claude/skills/mcp-server-audit/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditing an MCP server

Start here — do not reach for a scanner first

node scripts/audit-live-mcp.mjs                      # production
node scripts/audit-live-mcp.mjs http://localhost:3001

Zero dependencies, node built-ins only, installs nothing. Exit 1 on any FAIL. It covers the machine-checkable half of what the popular third-party scanners check (§4). Everything it prints is measured, never inferred — that matters, because the most common failure in MCP auditing is a confident report about a server nobody actually connected to.

Baseline for mcp.hellogrowthcrm.com on 2026-08-31: 2 fail · 5 warn · 12 pass. A new FAIL is a regression. Record the run in the audit report.


1. The checks a script cannot do — always do these by hand

The wire protocol can be perfect while the server confidently serves false information. This is where the real defects were found:

  • Are the numbers true? Call features_list, integrations_list, content_list_industries, pricing_get_plans and reconcile each against the codebase. On 2026-08-31 the server reported 630 integrations against 525 in the code, and a feature list of 58 against 232 screens / 135 catalogue entries / 99 public-catalog features. Nothing regenerates the mirror from the source of truth, so it drifts silently.
  • Do the URLs resolve? curl -o /dev/null -w "%{http_code}" every URL the server emits. A sameAs entry published as an entity signal was returning 404 while a second field in the same payload held a working one.
  • Are pricing / compliance / residency claims sourced? These end up quoted verbatim by AI assistants. Check against the canonical source, not against a draft someone pasted. Real values live in pricing_get_plans and countries_list.
  • Is the freshness stamp moving? Payloads carry synced_at. A stamp weeks old with no regeneration job is the same silent-rot failure as any generated file.

2. Traps specific to this server

Read the full file on GitHub · 151 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.

  1. 8d ago First seen · 151 lines · 110 tokens per session scan A fbb0a7282df2

Subscribe to this mod's changes

mcp-server-audit is a skill published in the GitHub repository MeruLocal/HelloGrowthCRMwebsite_MCP (0 stars, last pushed 5d ago), licensed MIT. It adds 110 tokens to every session and 2,024 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens