Your AI assistant can run fraud checks.
FraudCheck ships a native MCP server — the open protocol AI assistants use to call external tools. Connect it once with your API key, and Claude, ChatGPT, Grok, Gemini, Cursor, or any MCP-capable agent can screen an order, look up an IP, or run a sanctions check mid-conversation. Same checks, same limits, same billing as the REST API.
Connect your assistant
Claude Code:
claude mcp add --transport http fraudcheck https://fraudcheckapi.com/mcp --header "X-Api-Key: YOUR_API_KEY"
Or any MCP client that takes a JSON config:
{
"mcpServers": {
"fraudcheck": {
"type": "http",
"url": "https://fraudcheckapi.com/mcp",
"headers": { "X-Api-Key": "YOUR_API_KEY" }
}
}
}
| Assistant | How to connect |
|---|---|
| Claude Code | Run the one-line command above. |
| ChatGPT | Settings → Connectors → add a custom connector with the URL https://fraudcheckapi.com/mcp, choose API key authentication, and paste your key. |
| Grok | grok.com/connectors → New Connector → Custom → enter the same URL and your API key. |
| Gemini CLI | Add the JSON config above to your MCP settings (~/.gemini/settings.json, using httpUrl). |
| Cursor, VS Code & others | Paste the JSON config above into the client's MCP settings — any client that supports remote MCP servers works. |
Then just ask: "Screen this order — IP 9.9.9.9, email [email protected], shipping to DE." The assistant calls the tools and reads back the checks.
Machine-readable everything
Agents and tooling can discover the whole API without a human in the loop:
| /.well-known/mcp/server-card.json | MCP server discovery |
| /.well-known/api-catalog | API catalog (RFC 9727) |
| /openapi/v1.json | Full OpenAPI specification |
| /llms.txt | LLM-friendly product overview |
| /.well-known/oauth-authorization-server | OAuth discovery metadata |
MCP calls use your normal API key and count toward your plan like any REST call — nothing separate to set up or pay for.
Get your API key →Results are derived from publicly available databases and are provided as-is. Checks, not verdicts — your assistant reads them; you make the call.