What is mcp-integration-audit?

A review guide for deciding how a coding agent should connect to outside tools and services through MCP, a standard way for AI tools to access other systems.

Use it to choose local, project, or user-level settings, review a shared .mcp.json file, and plan safe connections to services such as GitHub, Sentry, databases, and documentation sources.

It helps prevent secrets from entering source control and avoids making integrations available to more people or projects than necessary.

How BlocUnited-LLC/mozaiks configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to BlocUnited-LLC/mozaiks. 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/BlocUnited-LLC/mozaiks/main/.agents/skills/mcp-integration-audit/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/BlocUnited-LLC/mozaiks

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/mcp-integration-audit/github.svg)](https://agentmods.dev/skills/blocunited-llc/mozaiks/mcp-integration-audit)

Your own site

<a href="https://agentmods.dev/skills/blocunited-llc/mozaiks/mcp-integration-audit"><img src="https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/mcp-integration-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/blocunited-llc/mozaiks/mcp-integration-audit"><img src="https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/mcp-integration-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 201 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00063	$0.00201
Opus 5.5	$0.00025	$0.00080
Sonnet 5.5	$0.00013	$0.00040
Haiku 4.5	$0.00006	$0.00020

Measured 2mo ago against content hash ecdf483941d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-integration-audit 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 2mo 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.

.agents/skills/mcp-integration-audit/SKILL.md · 19 lines

What it actually says

Audit this MCP integration topic: $ARGUMENTS

Return:

whether the integration should be local, project, or user scope
whether secrets can safely stay out of source control
whether a shared .mcp.json is appropriate for the repo
Windows-specific concerns for stdio servers, especially cmd /c npx usage
the smallest safe config pattern for the team

Prefer project-scoped MCP only for genuinely shared, repo-specific tools. Do not recommend checking credentials into the repo.

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.

2mo ago First seen · 19 lines · 63 tokens per session scan A ecdf483941d6

Subscribe to this mod's changes

mcp-integration-audit is a skill published in the GitHub repository BlocUnited-LLC/mozaiks (24 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 201 once invoked, about $0.0003 per session on Opus 5.5. 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 LLM agent-framework agentic-ai ai ai-agents genai

mcp-integration-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-integration-auditBlocUnited-LLC/mozaiks	Skill	24	yesterday	MIT	A	63	Claude Code
building-pydantic-ai-agentspydantic/pydantic-ai	Skill	21k	yesterday	MIT	A	92	Claude Code, Codex
pydantic-ai-harnesspydantic/pydantic-ai	Skill	21k	yesterday	MIT	A	197	Claude Code, Codex
migrating-langchain-to-pydantic-aipydantic/pydantic-ai	Skill	21k	yesterday	MIT	A	100	Codex
migrating-vercel-ai-sdk-and-eve-to-pydantic-aipydantic/pydantic-ai	Skill	21k	yesterday	MIT	A	107	Codex
migrating-claude-agent-sdk-to-pydantic-aipydantic/pydantic-ai	Skill	21k	yesterday	MIT	A	90	Codex
migrating-mastra-to-pydantic-aipydantic/pydantic-ai	Skill	21k	yesterday	MIT	A	73	Codex

mozaiks: Skill for Claude Code