Robin: AI-Powered Dark Web OSINT
Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.
Description from the maker (original English)
Hook Security phishing and training data for MSPs: click rates, overdue training, QBR numbers.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
Passed 2/3 checks · Runs on your computer
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
No key, nothing to install · Only the Claude desktop app (Windows or Mac), not the web or phone
Download the maker’s .mcpb file
The .mcpb file comes straight from the maker; we do not change it
Use Hook Security MCP and tell me what you can do for me, then show me one thing✓ If Claude says it is using Hook Security MCP or shows a Hook Security MCP tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect Hook Security MCP yet
Hook Security MCP runs on your computer, but ChatGPT can only connect servers that run on the web
A · Use an app that can connect Hook Security MCP
B · Others in Cybersecurity that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
Claude Code cannot connect Hook Security MCP yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect Hook Security MCP
Cursor cannot connect Hook Security MCP yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect Hook Security MCP
VS Code cannot connect Hook Security MCP yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect Hook Security MCP
HOOK_SECURITY_BASE_URL envHOOK_SECURITY_API_KEY secret required envHOOK_SECURITY_USER_AGENT envHOOK_SECURITY_MCP_READ_ONLY envHOOK_SECURITY_MCP_HTTP_TOKEN secret envPRINTING_PRESS_CLIENT_PROFILE envHOOK_SECURITY_NO_LOCAL_DATA envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
mcpb: https://github.com/Servosity/msp-skills/releases/download/hoBased on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 12, 2026
The registry name was verified with the GitHub account Servosity, which owns the repo
Code last changed today
GitHub could not identify the licence type; open the file to check
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: HOOK_SECURITY_API_KEY, HOOK_SECURITY_MCP_HTTP_TOKEN
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed today, and the latest version (0.1.0) reached the registry today.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Robin: AI-Powered Dark Web OSINT, HOL Guard, UniFi Network MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
Manage UniFi Network devices, clients, firewall, VLANs, VPNs, and more via MCP.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
The six agents MSP owners actually use (self-serve, works today):
| Your AI agent | How to install the Hook Security skill |
|---|---|
| Claude Desktop | Run installer, then Settings > Extensions to register hook-security-mcp (no JSON editing). |
| ChatGPT (paid plans) | Run installer, host hook-security-mcp over HTTPS with HOOK_SECURITY_MCP_HTTP_TOKEN set, then register it as a Developer Mode connector if your connector settings can send the bearer token. |
| Codex CLI | Paste the install prompt below. |
| Claude Code | Paste the install prompt below. |
| Claude Cowork | Paste the install prompt below. |
| GitHub Copilot (VS Code) | Run installer, add hook-security-mcp to mcp.json under the servers key, then pick Agent mode. |
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.
Big install base, but an honest heads-up: these are the remote / enterprise path, not the local binary you just installed.
| Agent | What it takes |
|---|---|
| Microsoft 365 Copilot / Copilot Studio | Not self-serve. Host hook-security-mcp over HTTPS with HOOK_SECURITY_MCP_HTTP_TOKEN set, then wire it into Copilot Studio (Tools > Add a tool > Model Context Protocol > Server URL) or a declarative agent, if it can send the bearer token. Needs a Copilot Studio license + tenant admin. See mcp-install.md. |
| Google Gemini | Gemini CLI is local - same as Claude Code. The Gemini app is remote - same HTTPS path as ChatGPT. See mcp-install.md. |
Skill-native agents (also covered): Hermes and OpenClaw read this skill's
SKILL.mddirectly *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.
.mcpbDownload 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
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, runiwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/hook-security/install.ps1 | iex. Then authenticate per the README and runhook-security-cli --helpto explore.
The same prompt works in any agent that can run shell.
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
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.
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.
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.
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 theopenclaw:frontmatter block.
OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.
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.
| Question your MSP keeps asking | Command | Reads |
|---|---|---|
| Which clients have the highest click rate? | hook-security-cli client-risk --top 10 | Live |
| Who clicked in this campaign and has not finished training? | hook-security-cli clicked-untrained --campaign cmp_88213 | Live |
| Who at this client clicked since July and has not finished? | hook-security-cli clicked-untrained --org org_4521 --since 2026-07-01 | Live |
| Which clients have people overdue on training? | hook-security-cli overdue-training --counts-only | Live |
| What are this client's QBR numbers? | hook-security-cli qbr org_4521 --days 90 | Live |
| Who reported this simulation? | hook-security-cli campaigns results list-campaign cmp_88213 --outcome reported --all | Live or local copy |
| How many billable users did each account have in October? | hook-security-cli billing --month 2026-10 --all | Live or local copy |
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.
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.
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.
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.
Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.
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