AI
ChatGPT
Add FFraud to ChatGPT as a custom MCP server: check how secure a website is, spot throwaway emails and risky IP addresses, free and with no key.
ChatGPT reaches FFraud through its MCP server at https://ffraud.com/api/mcp, added once as a plugin. Then ask in plain words: ChatGPT checks a whole website, an IP address, an email or a domain, and explains what FFraud found.
#Add FFraud to ChatGPT
- Open Plugins in ChatGPT, select the plus button, and choose Add custom MCP server.
- Name it FFraud.
- Under Connection, enter the server URL
https://ffraud.com/api/mcp. - For authentication, choose No authentication.
- Read the warning, select I understand and want to continue, then Create as a plugin.
- Find FFraud in your plugins and install it.
In a work or school workspace, an admin can switch custom MCP servers off. If the option is missing, ask yours.
#See that it is connected
In a new chat, type @ in the prompt box and select FFraud. Its settings list the five tools, and each can be switched on or off.
#Three prompts that work
Check a website
@FFraud How secure is example.com? Explain each finding in plain words and give me the fixes in order.ChatGPT runs site_check and walks through the findings, the most severe first, each with FFraud's exact fix. After you change the site, ask it to check again, fresh.
Spot a throwaway email
@FFraud Is newuser@mailinator.com a throwaway address?ChatGPT runs email_check and says whether the inbox is temporary, an alias, a role address or on the blacklist.
Weigh risky addresses
@FFraud Check these addresses from today's orders: 185.220.101.34 and 45.148.10.121. Which look risky, and why?ChatGPT runs ip_check on both and answers with each address's score, what it is (VPN, Tor, datacenter and so on) and FFraud's reason.
#Reading the answers
The model gets FFraud's full JSON and explains it in its own words. These are the fields worth asking about.
| Tool | Read first | Then |
|---|---|---|
| site_check | grade (A to F) and summary: how many things to fix and which comes first. | findings, the most severe first, each with its fix: the exact header line, DNS record or server setting. passed lists what is already right; checked_at says when the check ran. |
| ip_check | fraud_score (0 to 100) and risk (none, low, medium, high or critical). | reason says why in plain words; vpn, proxy, tor, relay and hosting say what kind of connection it is; recent_abuse and threat_tags say what it was seen doing. |
| email_check | email_type: temp (a throwaway inbox), alias, normal or invalid. | did_you_mean catches a typo in the domain; normalized_email spots one mailbox signing up twice. |
A VPN or a datacenter alone rarely means fraud: many real people use both. Ask the model to weigh them with the other signals and to quote FFraud's reason.
Does ChatGPT ask before it calls FFraud?
ChatGPT asks for confirmation before tools that write. FFraud's five tools tell it that they only read, so they run as you ask.
Can the model change anything through FFraud?
No. All five tools only read, and site_check only reads what any visitor of the site sees.
What does FFraud see when the model calls a tool?
The website, IP address, email or domain the call sends, the same as a check on ffraud.com. The conversation itself stays with your client.