Agent skill

MCP Dependency Drift Audit

by sickn33 in sickn33/agentic-awesome-skills

Statically audit MCP configs for mutable npm/npx package references before approval or CI, without executing discovered MCP servers.

MITAuto-check passedAgent Workflows

Install MCP Dependency Drift Audit

skills CLI
$ npx skills add sickn33/agentic-awesome-skills --skill mcp-dependency-drift-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sickn33/agentic-awesome-skills mcp-dependency-drift-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mcp-dependency-drift-audit .claude/skills/mcp-dependency-drift-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mcp-dependency-drift-audit
GitHub stars
47k
Used in
1 other repo
Token cost
~2k tokens
SKILL.md length
860 words
Files
1
Skills in repo
1,493
Repo updated
First seen
Licence
MIT

At a glance

Statically audit MCP configs for mutable npm/npx package references before approval or CI, without executing discovered MCP servers.

  • Works in 5 steps: Locate and read MCP configs without… → Use MCP Drift Check when already available → Apply the manual static rules → …
  • Tasks that involve MCP servers
  • SKILL.md covers Overview, When to Use This Skill, How It Works and Examples, plus 6 more sections
  • Calls uvx; reaches github.com

What it does

MCP Dependency Drift Audit is an agent skill from sickn33/agentic-awesome-skills. Statically audit MCP configs for mutable npm/npx package references before approval or CI, without executing discovered MCP servers.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol and npm. The repository describes itself as: AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes… The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/mcp-dependency-drift-audit”

Requirements

  • Node.js

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Locate and read MCP configs without executing them
  2. Use MCP Drift Check when already available
  3. Apply the manual static rules
  4. Recommend remediation without inventing versions
  5. Produce a bounded report

What it can do on your machine

Read from SKILL.md and the folder at commit 680176d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uvx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • site-creator-vinext-starter.surfaceproof.workers.dev

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Dependency Drift Audit loads about 2k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 860 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sickn33/agentic-awesome-skills at commit 680176d, republished under its MIT licence (© sickn33). 860 words, ~1,983 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-dependency-drift-audit/SKILL.md (or your agent's skills folder).
name
mcp-dependency-drift-audit
description
Statically audit MCP configs for mutable npm/npx package references before approval or CI, without executing discovered MCP servers.
category
security
risk
safe
source
https://github.com/tomelias10/mcp-drift-check
source_repo
tomelias10/mcp-drift-check
source_type
community
date_added
2026-09-25
author
tomelias10
tags
mcp, ai-security, supply-chain, devsecops, sarif
tools
claude, cursor, gemini, codex, windsurf
license
MIT

MCP Dependency Drift Audit

Overview

Audit Model Context Protocol configuration files for npm/npx package references that can resolve to different code after the configuration was reviewed. The workflow is deliberately static: it reads config text, classifies version selectors, and recommends reproducibility fixes without starting discovered MCP servers.

Dependency mutability is a review-boundary signal, not proof that a package is malicious, vulnerable, or compromised.

When to Use This Skill

  • Before approving .mcp.json, Cursor, VS Code, GitHub Copilot, Claude, or Windsurf MCP configuration.
  • When adding an MCP configuration gate to pull requests or CI.
  • During an AI-agent security review where npm/npx-backed MCP servers are configured.
  • When checking whether a previously reviewed MCP config can silently resolve to newer package code.

How It Works

Step 1: Locate and read MCP configs without executing them

Inspect known project paths such as .mcp.json, .github/mcp.json, .cursor/mcp.json, .vscode/mcp.json, and .windsurf/mcp.json, plus any MCP config explicitly supplied by the user.

Read them as text/JSON only. Never run a discovered command or args value as part of this audit. Stay inside the requested workspace by default; only include user-level/global MCP configuration if the user explicitly asks for machine-wide scope.

Step 2: Use MCP Drift Check when already available

If mcp-drift-check is already installed, use the workspace-scoped mode from the intended repo root:

bash
mcp-drift-check scan-workspace --markdown

For CI evidence:

bash
mcp-drift-check scan-workspace --sarif mcp-drift.sarif --markdown

If the scanner is not installed, explain that the following command fetches the open-source scanner from GitHub and get user approval before running it:

bash
uvx --from git+https://github.com/tomelias10/mcp-drift-check mcp-drift-check scan-workspace --markdown

If the user declines network access or installation, continue with the manual rules below.

Step 3: Apply the manual static rules

For npm/npx-style package selectors:

SelectorClassificationReason
package@1.2.3SAFEExact package version is reproducible.
bare package or @scope/packageHIGHA later resolution can select different package code.
package@latestHIGHThe selector is explicitly mutable.
package@^1.2.0, ~1.2.0, >=1.2.0, wildcardMEDIUMResolution can change within the allowed range.
local path, script, binary, unknown executableREVIEWnpm version-drift rules do not establish update behavior.

Treat -y / --yes as context only. It suppresses interactive confirmation but is not a vulnerability by itself.

Step 4: Recommend remediation without inventing versions

For mutable npm/npx references, recommend pinning to an exact version that the team has actually reviewed and then updating that pin deliberately.

Do not guess the version to pin. If registry lookup is needed, explain that it requires network access and ask before querying it.

Pinning improves reproducibility. It does not establish package provenance, vulnerability status, authorization safety, prompt-injection resistance, or runtime isolation.

Step 5: Produce a bounded report

Return:

ConfigMCP serverPackage/referenceClassificationWhyRecommended next step

Then state:

  • No MCP servers were executed during the audit.
  • Mutable dependency references are review/reproducibility signals, not breach claims.
  • A clean dependency-drift result is not a complete MCP security assessment.

Examples

Example 1: Audit before approval

User: Audit this repo's MCP config before we approve it. Do not run any MCP servers.

Expected shape:

text
.mcp.json | browser | @example/browser-mcp@latest | HIGH
Reason: @latest can resolve to different package code later.
Next step: pin the exact version your team reviews and update it deliberately.

No MCP servers were executed.
Example 2: Add a CI gate

For GitHub Actions:

yaml
- uses: actions/checkout@v4
- uses: tomelias10/mcp-drift-check@v0

MCP Drift Check can also emit SARIF 2.1.0 for GitHub Code Scanning. The action defaults to workspace-only discovery; machine-wide user-level scanning remains an explicit scan-all choice.

Show full SKILL.md (346 more words)Show less

Best Practices

  • ✅ Read config text only during discovery and classification.
  • ✅ Keep the default scope to the requested workspace/repository.
  • ✅ Separate reproducibility findings from vulnerability or compromise claims.
  • ✅ Pin only a version the team has actually reviewed.
  • ✅ Keep sensitive config values out of reports and public issues.
  • ❌ Do not execute server commands found in a config to "verify" a static finding.
  • ❌ Do not treat a clean result as a general MCP security guarantee.

Limitations

  • This workflow only covers dependency mutability/review drift for package-backed MCP configuration.
  • It does not assess prompt injection, tool poisoning, OAuth/authorization, server implementation flaws, malware, provenance, or runtime sandboxing.
  • Local executables and non-npm launch paths require separate review.
  • A static config can be reproducible and still unsafe for other reasons.

Security & Safety Notes

  • The default workflow is read-only, local, and workspace-scoped.
  • Never execute discovered MCP server commands during this audit.
  • Never include credentials, tokens, private headers, or secret values in the output.
  • The optional uvx path makes a network fetch from the declared GitHub source; obtain user approval before running it.
  • If deeper active testing is requested, stop and establish explicit authorization and scope before any intrusive action.

Common Pitfalls

  • Problem: Calling an unpinned dependency a vulnerability. Solution: Describe it as a reproducibility/review-drift signal unless separate evidence establishes security impact.
  • Problem: Pinning to today's registry version without knowing what was reviewed. Solution: Ask for the reviewed version or, with approval, reconstruct relevant package history; do not guess.
  • Problem: Treating -y as the core finding. Solution: Report it only as context; the version selector determines the dependency-drift classification.
  • Problem: Scanning user-level MCP configs when the user only asked about one repo. Solution: Use scan-workspace by default; use scan-all only when machine-wide scope is explicit.
  • @mcp-server-security - Broader MCP server hardening, authentication, authorization, transport, and runtime controls.
  • @supply-chain-security - Broader software supply-chain assessment beyond MCP configuration.
  • @sast-scanning - Static application-security analysis for source code rather than MCP launch configuration.

Additional Resources

© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/mcp-dependency-drift-audit of sickn33/agentic-awesome-skills.

Open the folder on GitHubat commit 680176d

Used in 1 other repository

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in sickn33/agentic-awesome-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

MCP Dependency Drift Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP Dependency Drift Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Dependency Drift Audit this skillsickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassMIT
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Yahoo Finance2gadicc/yahoo-finance2801—~1.8kAutomated safety check: PassMIT
Workflow Schema Tuningbreaking-brake/cc-wf-studio5.4k—~1.3kAutomated safety check: PassCustom licence
Paseo Plugin Buildergetpaseo/paseo20k—~9.4kAutomated safety check: PassCustom licence
Context Mode Doctormksglu/context-mode26k—~262Automated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Yahoo Finance2

    gadicc/yahoo-finance2

    A skill your agent uses when building with the yahoo-finance2 TypeScript/Deno/npm library, using its Yahoo Finance data modules, CLI, or MCP server, or contributing to the yahoo-finance2 repository…

    801 GitHub stars~1.8k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed
  • Workflow Schema Tuning

    breaking-brake/cc-wf-studio

    Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.

    5.4k GitHub stars~1.3k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Paseo Plugin Builder

    getpaseo/paseo

    Builds, installs and troubleshoots trusted local Paseo plugins, from lifecycle hooks and slash commands to screens, themes and timeline renderers.

    20k GitHub stars~9.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Context Mode Doctor

    mksglu/context-mode

    Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

    26k GitHub stars~262 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

    74k GitHub starsUsed in 1 repo~975 tokens
    Agent WorkflowsAuto-check passed

More from sickn33/agentic-awesome-skills

All 1,493 skills in this repo
  • Liuguang Banlan UI

    sickn33/agentic-awesome-skills

    Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Find Complementary Founders

    sickn33/agentic-awesome-skills

    Guides an agent through assessing its own owner for cofounder fit, publishing an approved profile, and ranking complementary profiles other agents published for their owners.

    47k GitHub starsUsed in 1 repo~4.8k tokens
    Auto-check passed
  • Whatsapp Cloud API

    sickn33/agentic-awesome-skills

    Integracao com WhatsApp Business Cloud API (Meta). An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~4.5k tokens
    Auto-check passed
  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

Categories

Questions about MCP Dependency Drift Audit

What does MCP Dependency Drift Audit do?

Statically audit MCP configs for mutable npm/npx package references before approval or CI, without executing discovered MCP servers. MCP Dependency Drift Audit is an agent skill from sickn33/agentic-awesome-skills. Statically audit MCP configs for mutable npm/npx package references before approval or CI, without executing discovered MCP servers.

When should I use MCP Dependency Drift Audit?

MCP Dependency Drift Audit fits situations like: tasks that involve MCP servers.

How do I install MCP Dependency Drift Audit in Claude Code?

Run `npx skills add sickn33/agentic-awesome-skills --skill mcp-dependency-drift-audit -a claude-code`. Or copy the skill folder (skills/mcp-dependency-drift-audit in sickn33/agentic-awesome-skills) into .claude/skills/mcp-dependency-drift-audit in your project. Claude Code loads it when a task matches its description.

How do I install MCP Dependency Drift Audit in Codex?

Run `npx skills add sickn33/agentic-awesome-skills --skill mcp-dependency-drift-audit -a codex`. Or copy the skill folder (skills/mcp-dependency-drift-audit in sickn33/agentic-awesome-skills) into .agents/skills/mcp-dependency-drift-audit in your project. Codex loads it when a task matches its description.

Can I use MCP Dependency Drift Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sickn33/agentic-awesome-skills --skill mcp-dependency-drift-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-dependency-drift-audit, .gemini/skills/mcp-dependency-drift-audit, .github/skills/mcp-dependency-drift-audit and .opencode/skills/mcp-dependency-drift-audit in your project.

What does MCP Dependency Drift Audit need to run?

Going by SKILL.md and its folder, MCP Dependency Drift Audit needs the command-line tools its instructions call (uvx). Our summary lists: Node.js.

Does MCP Dependency Drift Audit access the network?

SKILL.md names 2 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: site-creator-vinext-starter.surfaceproof.workers.dev. This is read from the text; nothing was executed.

Is MCP Dependency Drift Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MCP Dependency Drift Audit use?

MCP Dependency Drift Audit is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP Dependency Drift Audit use?

About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP Dependency Drift Audit?

Skills that share tags, products or a category with MCP Dependency Drift Audit: MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), Yahoo Finance2 (gadicc/yahoo-finance2, 801 stars), Workflow Schema Tuning (breaking-brake/cc-wf-studio, 5.4k stars) and Paseo Plugin Builder (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Dependency Drift Audit?

sickn33 (a GitHub user) maintains it in sickn33/agentic-awesome-skills, which has 47,379 GitHub stars. The repository holds 1,493 skills in this directory. The repository was last updated on October 9, 2026.

Source: sickn33/agentic-awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.