security-investigator: Skill for Claude Code

.github/skills/mcp-usage-monitoring/SKILL.md

mcp-usage-monitoring is a skill for Claude Code, Codex from SCStelz/security-investigator. It costs 159 tokens per session (30,419 once invoked), scanned A, original, MIT.

A security-monitoring guide for tracking how Model Context Protocol (MCP) servers—AI-connected tools—are used in Microsoft Sentinel and Defender XDR.

In plain words
What is it for?
Use it to monitor Graph, Sentinel, and Azure MCP servers, investigate tool usage, and review related activity logs and queries.
Why use it?
It helps security teams see MCP activity, identify the user or application involved, and audit this privileged access channel.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is SCStelz/security-investigator's own configuration. It tells Claude Code and Codex how to work on security-investigator 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 security-investigator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SCStelz/security-investigator. 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/SCStelz/security-investigator/main/.github/skills/mcp-usage-monitoring/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SCStelz/security-investigator

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-usage-monitoring

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/scstelz/security-investigator/mcp-usage-monitoring"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/mcp-usage-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 30,419 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 warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 140
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 1837
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Agent Snooping · line 1831
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 1840
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 1860
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Excessive Agency · line 247
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00159 $0.30419
Opus 5 $0.00079 $0.15210
Sonnet 5 $0.00032 $0.06084
Haiku 4.5 $0.00016 $0.03042

Measured 13d ago against content hash 9ca84187a7de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-usage-monitoring 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 13d 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.

.github/skills/mcp-usage-monitoring/SKILL.md · 1,866 lines

How it starts

The opening of the file, as written. The whole thing — 1,866 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Usage Monitoring — Instructions

Purpose

This skill monitors and audits Model Context Protocol (MCP) server usage across your Microsoft Sentinel and Defender XDR environment. MCP servers are AI-powered tools that enable language models to interact with Microsoft security services — and like any privileged access channel, they require monitoring.

What this skill tracks:

MCP Server Telemetry Source Key Identifier
Microsoft Graph MCP Server MicrosoftGraphActivityLogs AppId = e8c77dc2-69b3-43f4-bc51-3213c9d915b4
Sentinel Data Lake MCP CloudAppEvents RecordType 403, Interface = IMcpToolTemplate
Sentinel Triage MCP MicrosoftGraphActivityLogs + SigninLogs AppId = 7b7b3966-1961-47b5-b080-43ca5482e21c ("Microsoft Defender Mcp") — dedicated AppId with full user attribution via delegated cert auth
Azure MCP Server AzureActivity No dedicated AppId — uses DefaultAzureCredential
Sentinel Data Lake — Direct KQL CloudAppEvents RecordType 379, Operation = KQLQueryCompleted
Workspace Query Sources (Analytics Tier) LAQueryLogs All clients querying Log Analytics workspace

What this skill detects:

  • Graph API call volume, trends, and endpoint diversity via MCP
  • Sensitive/high-risk Graph endpoint access (PIM, credentials, Identity Protection)
  • Sentinel workspace query patterns by client application
  • User vs. Service Principal attribution across all MCP channels
  • Cross-server user analysis — identifies users with broadest MCP footprint (multiple server types, highest call volume)
  • Azure ARM operations potentially originating from Azure MCP Server
  • Non-MCP platform query sources for governance context (Sentinel Engine, Logic Apps)
  • Sentinel Data Lake MCP tool usage — tool call breakdown (query_lake, list_sentinel_workspaces, search_tables, etc.), success/failure rates, execution duration, tables accessed via CloudAppEvents (Purview unified audit)
  • MCP-driven vs Direct KQL delineation — distinguishes Data Lake queries initiated via MCP tools (RecordType 403, Interface IMcpToolTemplate) from direct KQL queries (RecordType 379) and Analytics tier queries (LAQueryLogs)
  • Anomalous access patterns: new users, new endpoints, volume spikes, error surges
  • MCP server usage as a proportion of total workspace activity

Read the full file on GitHub · 1,866 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 1,866 lines · 159 tokens per session scan A 9ca84187a7de

Subscribe to this mod's changes

mcp-usage-monitoring is a skill published in the GitHub repository SCStelz/security-investigator (245 stars, last pushed 4d ago), licensed MIT. It adds 159 tokens to every session and 30,419 once invoked, about $0.0008 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.

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