SML Risk Firewall
Pre-trade risk checks for agent trades: orders vs your limits, signed receipts.
Description from the maker (original English)
Detect fake-recruiter and job-offer scams using free OSINT. No API keys.
These three are never merged into one score: opinions, measurements and popularity are different things.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"jobverify": {
"command": "uvx",
"args": [
"jobverify-mcp"
]
}
}
}Run this in your terminal
claude mcp add jobverify -- uvx jobverify-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"jobverify": {
"command": "uvx",
"args": [
"jobverify-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"jobverify": {
"type": "stdio",
"command": "uvx",
"args": [
"jobverify-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
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 7, 2026
The registry name was verified with the GitHub account yessGlory17, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
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
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 –, and the latest version (0.1.0) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: SML Risk Firewall, ipdata MCP by usefulapi, MaxMind minFraud MCP by usefulapi
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Pre-trade risk checks for agent trades: orders vs your limits, signed receipts.
Look up location, network, company and threat data for IP addresses and ASNs in ipdata.
MCP server for MaxMind minFraud — score transactions for fraud risk from your AI assistant.
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.
Check whether a recruiter or job offer is real — before you reply.
You get a message: *"We loved your profile and want to offer you a great remote job."* It sounds real. The company has a logo. The recruiter has a photo. But something feels off.
JobVerify helps you find out — in seconds — whether it's genuine or a scam.
You paste the recruiter's message (or a company name, a link, or an email) and ask your AI assistant. JobVerify quietly runs the same background checks a professional investigator would, then gives you a plain-English answer: looks legit, be careful, or this is almost certainly a scam — and *why*.
Fake recruiter and job-offer scams are everywhere, and they're convincing. On your own, you're left guessing:
By the time you notice, your time, your personal details — or your money — may already be gone.
JobVerify cross-checks the offer against dozens of free, public information sources and combines the clues into one clear verdict:
No account, no sign-up, and none of your data is sold or stored. It simply helps you not get fooled.
You don't need to learn anything technical. It's a three-step conversation:
[!NOTE]
JobVerify never logs into or scrapes LinkedIn. It only looks at information that is already
public, and reads website history through the Internet Archive — the safe, legal way to check
how long a profile or company page has *really* existed (scammers rely on brand-new throwaway accounts).
Think of it as a checklist a careful friend — who happens to be a fraud investigator — would run for you:
| Area | The question it answers |
|---|---|
| The message | Does this match known scam playbooks (advance fees, fake tasks, crypto, urgency)? |
| The company | Is it a real, registered business? Any recent scam reports? Is the office address real? |
| The person | Is the email real and deliverable? Is the phone valid? Are the photos/usernames reused elsewhere? |
| The links | Is the domain brand-new? A look-alike of a real brand? On any phishing/malware blocklist? |
| The money | Is the crypto wallet they gave you already flagged in scam databases? |
| The history | How long has this profile or website *actually* been online? |
Ask your assistant something as simple as:
Is this recruiter legit?
"Hi! I'm a talent partner at Example Corp. We loved your profile and want to offer you a remote role at $45/hr. To get started, please purchase $200 of onboarding equipment through this link — you'll be fully reimbursed on day one. Let's continue on Telegram: @examplecorp_hr"
JobVerify will pick out Example Corp, the link, and the Telegram hand-off, check each one, and reply with something like: *"⚠️ High risk — the company has no public registration, the link was registered 4 days ago, and asking you to pay upfront and move to Telegram are textbook scam signals."*
No cloning. No virtualenv. No manual install. JobVerify runs straight from GitHub — you only paste a few lines into your AI assistant's config, and it fetches and launches itself on demand.
[!NOTE]
The only thing you need once is uv — a tiny, free helper that runs
the tool for you:
- macOS / Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Windows:
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
Add this to your claude_desktop_config.json, then restart Claude:
{
"mcpServers": { "jobverify": { "command": "uvx", "args": ["jobverify-mcp"] } } }
One line in your terminal:
claude mcp add jobverify -- uvx jobverify-mcp
The first run takes a few seconds while it downloads the tool; after that it's instant.
Paste a suspicious message and ask *"Is this offer legit?"* — or run the built-in `analyze` prompt. That's it.
For the curious: the full toolbox
Under the hood, the AI assistant orchestrates these individual checks (all free, no keys):
| Tool | What it checks |
|---|---|
extract_entities | Pulls emails, links, phones, wallets, and profile URLs out of a message |
check_scam_patterns | Matches text against known scam tactics |
check_email / check_email_footprint | Email deliverability + linked social accounts |
check_domain / check_domain_auth | Domain age, registrar, and whether it can be spoofed |
check_typosquatting / find_lookalike_domains | Look-alike / imposter domains |
check_url / check_ip | Phishing & malware blocklists |
check_certificate_transparency | A site's certificate & subdomain history |
parse_email_headers | Origin, SPF/DKIM/DMARC, and mismatches in raw email headers |
check_phone | Phone number validity and region |
check_crypto_address | Known-scam crypto wallet databases |
verify_company / search_company_news / verify_address | Business registration, press, and real address |
check_github_org / check_username | Whether an org/username really exists and how old it is |
check_wayback / fetch_archived_page | Internet Archive history & content (the legal way to read a page) |
There's also a single `analyze` prompt that runs the whole extract → check → verdict flow for you.
JobVerify is a decision-support tool. Its signals are probabilistic and may be incomplete or wrong. Always use your own judgment, and never treat a result as a definitive statement about any individual or organization.
MIT — use it, share it, and help people stay safe.