mcp-security

mcp-security is a skill for Claude Code, Codex from GoldenWing-360/claude-security-skills. It costs 71 tokens per session (1,914 once invoked), scanned A, original, MIT.

A security review guide for Model Context Protocol servers, which let an AI agent use external tools and data. It covers what servers can do, risky permissions, secrets, suspicious packages, and access changes over time.

In plain words
What is it for?
Use it before installing an MCP server, after a security advisory or version update, when investigating an unexpected agent action, or during regular access reviews.
Why use it?
It helps reveal what an agent has been allowed to access or change. This reduces the risk of excessive permissions, unexpected writes, and attacks that pass information between connected tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it before installing an MCP server, after a security advisory or version update, when investigating an unexpected agent action, or during regular access reviews.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goldenwing-360/claude-security-skills/mcp-security
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.

Any agent
npx skills add GoldenWing-360/claude-security-skills --skill mcp-security
Clone the repo
git clone --depth 1 https://github.com/GoldenWing-360/claude-security-skills

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.

agentmods badge for mcp-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/mcp-security/github.svg)](https://agentmods.dev/skills/goldenwing-360/claude-security-skills/mcp-security)
Your own site
<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/mcp-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/mcp-security/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-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/mcp-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/mcp-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,914 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 $0.00071 $0.01914
Opus 5 $0.00036 $0.00957
Sonnet 5 $0.00014 $0.00383
Haiku 4.5 $0.00007 $0.00191

Measured 11d ago against content hash e2614502fd6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-security 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 11d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

ls -la ~/.claude/mcp.json ~/.claude/settings.json 2>/dev/null

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

mcp-security/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Security

The Model Context Protocol turns an LLM into a system that can act. That makes every MCP server a new piece of attack surface, with three properties that classical security tooling does not yet handle well:

  1. Capability creep — adding an MCP often adds dozens of tools at once. Most users never read what they granted.
  2. LLM as confused deputy — the LLM will happily call any tool that fits the conversational context, including ones the user did not mean to invoke.
  3. Cross-MCP attacks — one MCP can return data that triggers another MCP to act (indirect prompt injection across the tool boundary).

This skill is the audit/hardening counterpart to ai-agent-guardrails and prompt-injection-defense.

When to invoke

  • A new MCP server is being installed
  • An MCP advisory or version bump landed
  • A contractor's or shared machine needs an audit
  • An LLM agent made a write you did not expect — start here to scope what it could have done
  • Periodic re-audit (monthly is reasonable for active stacks)

Step 1 — Inventory

MCP config can live in several places. Find them all.

# Claude Code / claude-desktop / cursor / windsurf — common locations
ls -la ~/.claude/mcp.json ~/.claude/settings.json 2>/dev/null
ls -la ~/Library/Application\ Support/Claude/claude_desktop_config.json 2>/dev/null
ls -la ~/.cursor/mcp.json ~/.codeium/windsurf/mcp_config.json 2>/dev/null

# Project-local MCPs
find ~/Code -maxdepth 3 -name '.mcp.json' -o -name 'mcp.json' 2>/dev/null

# Plugin-bundled MCPs (Claude Code plugin marketplace etc.)
ls -la ~/.claude/plugins/ 2>/dev/null

For each MCP you find, record: name, transport (stdio / http / sse), command or URL, scopes / API keys it holds, who installed it and when.

Step 2 — Risk-classify each MCP

Assign each MCP a tier. Re-do this whenever its capabilities change.

Tier Examples What it means
🟢 Read-only-local filesystem with --readonly, sqlite read, jq Worst case: information disclosure of local files
🟡 Read-only-remote search APIs, read-only SaaS (status pages, dashboards) Worst case: PII exfil via the LLM, query-quota burn
🟠 Write-to-staging dev-only DB, sandbox APIs (Stripe test, sandbox WP) Worst case: corrupted staging data, recoverable
🔴 Write-to-prod hosting panel, prod DB, CMS, DNS, CI triggers Worst case: customer impact, data loss, hard to undo
Spend-money or send-on-behalf payment APIs, email send, SMS, ad-budget changes Worst case: financial loss, reputation damage, fraud

Read the full file on GitHub · 140 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. 11d ago First seen · 140 lines · 71 tokens per session scan A e2614502fd6f

Subscribe to this mod's changes

mcp-security is a skill published in the GitHub repository GoldenWing-360/claude-security-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,914 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ux-audit

Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the…

jezweb/claude-skills · 217 tokens

tanstack-start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 +…

jezweb/claude-skills · 115 tokens

design-loop

Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…

jezweb/claude-skills · 130 tokens

product-showcase

Generate a comprehensive marketing website for a web app — multi-page with real screenshots, animated GIF walkthroughs, feature deep-dives, and workflow demonstrations. Browses the running app, captures screens and sequences, and produces a deployable site that actually teaches people what the product does. Especially…

jezweb/claude-skills · 117 tokens

google-apps-script

Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…

jezweb/claude-skills · 89 tokens

cloudflare-api

Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide…

jezweb/claude-skills · 141 tokens