# Hook Security MCP

This MCP server for Claude Code connects an AI agent to Hook Security data. It surfaces phishing click rates, training status, and figures for client QBRs.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 87 repo stars
- Author: Servosity
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Servosity/msp-skills/tree/HEAD/skills/hook-security
- Updated: 2026-10-24
- Security check: automated, 2026-11-17 (text) — warning: a command downloads a script from raw.githubusercontent.com and runs it right away; a PowerShell command downloads a script from raw.githubusercontent.com and runs it right away. Do not run such commands without an explicit yes from the human.
- HTML: https://affpapa.org/en/nevibecode/mcp/hook-security-mcp

## What it does

The server connects to the Hook Security API and gives an agent client data: phishing-link click rates, people who clicked but have not finished training, overdue training, and QBR figures. Requests to Hook Security require authentication.

The installer places `hook-security-cli` and `hook-security-mcp` in the user’s executable path; Claude Code discovers the skill through `SKILL.md`. For remote access, run the server with HTTP transport on an HTTPS host and set `HOOK_SECURITY_MCP_HTTP_TOKEN`.

## Requirements
- Environment variables: `HOOK_SECURITY_BASE_URL`, `HOOK_SECURITY_API_KEY`, `HOOK_SECURITY_USER_AGENT`, `HOOK_SECURITY_MCP_READ_ONLY`, `HOOK_SECURITY_MCP_HTTP_TOKEN`, `PRINTING_PRESS_CLIENT_PROFILE`, `HOOK_SECURITY_NO_LOCAL_DATA` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- check client phishing-link click rates
- find people who clicked and left training unfinished
- identify overdue training
- gather Hook Security figures for a client QBR

## Example prompts
- Show phishing-link click rates across our clients.
- Find people who clicked a phishing link but have not finished training.
- Prepare Hook Security figures for a client QBR.

## Similar
- [firebase-security-rules-auditor](https://affpapa.org/en/nevibecode/skills/firebase-security-rules-auditor.md) — skill · 150300 installs
- [HTTP Security Headers — HSTS, CSP, Score 0-100](https://affpapa.org/en/nevibecode/mcp/http-security-headers-hsts-csp-score-0-100.md) — MCP server · 4473 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 116100 installs
- [security-and-hardening](https://affpapa.org/en/nevibecode/skills/security-and-hardening.md) — skill · 89500 installs
- [cloud-security-scanner](https://affpapa.org/en/nevibecode/mcp/cloud-security-scanner.md) — MCP server · 3008 installs
- [middleBrick | API-Security](https://affpapa.org/en/nevibecode/mcp/middlebrick-api-security.md) — MCP server · 2930 installs

From the same set: [servosity/msp-skills](https://affpapa.org/en/nevibecode/by/servosity/msp-skills.md) — 107 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
