Hook Security MCP

Hook Security + AI - for ChatGPT, Claude, GitHub Copilot, Microsoft 365 Copilot, Gemini, and any agent that speaks MCP

Unofficial. Community-built Claude Code Skill and MCP server for the Hook Security

API. Not affiliated with, endorsed by, or sponsored by Hook Security Inc.

Full skill page - install, outcomes, safety model.

Phishing click rates, who clicked and has not finished training, overdue training and QBR numbers, across every client. Works with the AI you already use - ChatGPT (Plus/Pro+), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Microsoft 365 Copilot / Copilot Studio and Google Gemini via the remote path. Free, open source, runs on your laptop. Built for MSP owners. No code required.

Works with your agent

The six agents MSP owners actually use (self-serve, works today):

For ChatGPT, run hook-security-mcp --transport http with HOOK_SECURITY_MCP_HTTP_TOKEN set, on an HTTPS host; every request sends that token. See mcp-install.md.

Also for the Microsoft and Google stacks

Big install base, but an honest heads-up: these are the remote / enterprise path, not the local binary you just installed.

Skill-native agents (also covered): Hermes and OpenClaw read this skill's SKILL.md directly *and* speak MCP - see their install sections below. Also works with Cursor, Windsurf, Cline, Continue.dev, and Zed via MCP. Full per-tool wire-up: [docs/which-agent.md](../../docs/which-agent.md).

Run more than one agent? Install across all 51+ supported agents in one command: npx skills add Servosity/msp-skills@latest (requires Node.js, then run the per-skill installer for the CLI/MCP binaries). See docs/which-agent.md.

Install in 60 seconds

Fastest for Claude Desktop - one-click .mcpb

Download Hook Security MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every Hook Security release on the releases page.)

Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:

/plugin marketplace add Servosity/msp-skills

/plugin install hook-security@msp-skills

Path A - paste one prompt into your AI agent (recommended)

Copy this into Claude Code, Codex CLI, or Claude Cowork:

Install the Hook Security Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/hook-security/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/hook-security/install.ps1 | iex. Then authenticate per the README and run hook-security-cli --help to explore.

The same prompt works in any agent that can run shell.

Path B - run the installer yourself

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/hook-security/install.ps1 | iex

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/hook-security/install.sh)

The installer drops both hook-security-cli (the CLI) and hook-security-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.

Verify:

hook-security-cli --version

Upgrade to the latest version

The installer always fetches the current release - re-run it to upgrade:

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/hook-security/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/hook-security/install.ps1 | iex

Claude Desktop .mcpb users: download the latest .mcpb (top of this section) and re-select it in Settings > Extensions. Claude Code plugin users: /plugin update hook-security@msp-skills.

Add to Claude Desktop, GitHub Copilot, Gemini CLI, Microsoft 365 Copilot, or another MCP client

After the installer runs, see [mcp-install.md](./mcp-install.md) and [docs/which-agent.md](../../docs/which-agent.md) for the per-agent wire-up - one section per agent, including the GitHub Copilot servers key and the remote Microsoft 365 Copilot / Copilot Studio path. Claude Desktop's Settings > Extensions panel is the simplest path; the MCP config block (for users who prefer editing JSON) is documented in mcp-install.md.

Install for Hermes

From the Hermes CLI:

hermes skills install servosity/msp-skills/skills/hook-security --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/hook-security --force

Hermes speaks MCP natively, so it can also use the hook-security-mcp server directly - same install path, same env vars.

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the hook-security skill from https://github.com/servosity/msp-skills/tree/main/skills/hook-security. The skill defines how its required CLI (hook-security-cli) can be installed via the openclaw: frontmatter block.

OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.

Authenticate

Set the credentials the CLI needs (from your Hook Security portal):

HOOK_SECURITY_API_KEY=<value> hook-security-cli doctor

$env:HOOK_SECURITY_API_KEY="<value>"; hook-security-cli doctor

doctor checks config and paths, then sends one authenticated read to GET /v1/organizations, and reports whether Hook accepted the key.

What this skill does

client-risk needs an MSP key. "Finished" means every enrollment that was not cancelled is completed; completion dates are not compared with click dates, and courses are not matched to campaigns. List commands return one page unless you pass --all. search and sql read the local copy, so run hook-security-cli sync first or they answer empty.

Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.

What makes this different

Hook has its own remote MCP connection, and it is the shortest path if you only want to chat with your data. This connector runs on your computer and adds what a chat session does not give you: a command line for scripts and scheduled reports, an optional local SQLite copy for search and sql, and fixed commands whose output has the same fields every run.

clicked-untrained checks click results against enrollments. client-risk computes a fleet click rate from total clicks over total sent, never an average of client rates. qbr combines the organization, its summary, its newest campaigns and its overdue training, and fails rather than leave a section out. Each answer reports what it could not count, such as a client Hook marks too_large or a scan that stopped at --max-scan-pages.

The pain this closes

Hook's own announcement says the answers are "spread across a campaign page, a report and a training list", and describes the MSP need as "one question across every client, instead of opening each one." Its QBR template asks for click rate, training completion and report rate with trends, for every client, every quarter.

See pain-point.md for the longer narrative.

Frequently asked questions

Does this work with ChatGPT?

Yes, on Plus, Pro, Team, Business, Enterprise, and Education plans (Free tier does not yet expose Developer Mode). ChatGPT connects to remote MCP servers over HTTPS, not local stdio binaries. The Hook Security MCP server runs locally over stdio by default. Its HTTP mode (hook-security-mcp --transport http) serves http://127.0.0.1:7777/mcp, refuses to start until HOOK_SECURITY_MCP_HTTP_TOKEN is set, requires Authorization: Bearer on every request, and needs --tls-cert/--tls-key for any other address. See mcp-install.md. Step-by-step in mcp-install.md.

Does this work with Codex, Cursor, Windsurf, Cline, Copilot, or Gemini?

Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.

Do I need to know how to code?

No. The recommended install is to paste one sentence into Claude Code or Codex - your agent reads SKILL.md and does the install. The fallback is a