FraudLabs Pro for AI agents

FraudLabs Pro is an online payment fraud detection service that screens orders to help merchants reduce chargebacks, used by ecommerce stores protecting themselves from fraudulent orders. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Security and identityAPI keyMCP + RESTfraudlabspro.com
AUDIT LOG · FRAUDLABS PROPOLICY: acme-support
09:41:07 · claude · u_8f2read
fraudlabs_pro.get_order_result2
Get FraudLabs Pro Order Result (v2)✓ allowed · 212ms
09:41:08 · claude · u_8f2read
fraudlabs_pro.get_sms_verification_result
Get SMS Verification Result✓ allowed · 164ms
09:41:09 · claude · u_8f2write
fraudlabs_pro.create_account
Create FraudLabs Pro Reseller Sub-Account✓ approved · approved by user
EVERY FRAUDLABS PRO CALL, ON THE RECORD
01 · USE CASES

What agents do in FraudLabs Pro.

01

Screen a new order

Screen an order for fraud signals right after checkout, before it ships.

02

Check an order's fraud result

Get an order's fraud screening result to decide whether manual review is needed.

03

Confirm before flagging an order

Route a flagged order's feedback through approval, since it affects the merchant's fraud model.

02 · ACTIONS

8 FraudLabs Pro actions, graded by risk.

Every FraudLabs Pro action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

2

Look things up. Allowed by default.

  • fraudlabs_pro.get_order_result2
    Get FraudLabs Pro Order Result (v2)
  • fraudlabs_pro.get_sms_verification_result
    Get SMS Verification Result

write

6

Create and change things. Allow, or ask the user first.

  • fraudlabs_pro.create_account
    Create FraudLabs Pro Reseller Sub-Account
  • fraudlabs_pro.send_sms_verification
    Send SMS OTP Verification
  • fraudlabs_pro.subscribe_plan
    Subscribe Reseller Plan
  • fraudlabs_pro.flp_screen_order
    FraudLabs Pro Screen Order
  • fraudlabs_pro.flp_feedback_order
    FLP Feedback Order
  • fraudlabs_pro.webhook_order_status_changed
    Test Order Status Changed Webhook Delivery

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

FraudLabs Pro in three steps.

  1. 01Your users connect FraudLabs ProThey add their FraudLabs Pro api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create FraudLabs Pro Reseller Sub-Account” can wait for the user to approve.
  3. 03Any agent can actYour agent calls FraudLabs Pro through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('fraudlabs_pro', {
  read: 'allow',
  write: 'ask',        // create_account
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How FraudLabs Pro connects.

Users add their FraudLabs Pro api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same FraudLabs Pro connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use FraudLabs Pro from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

FraudLabs Pro and Arc0, answered.

Q01

Can I use FraudLabs Pro with Claude, ChatGPT or Cursor?

Yes. Connect FraudLabs Pro to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the FraudLabs Pro actions you allow.

Q02

How do users connect FraudLabs Pro?

Users add their FraudLabs Pro api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which FraudLabs Pro actions can my agent take?

8 in total: 2 read, 6 write and 0 destructive, such as “create FraudLabs Pro Reseller Sub-Account”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in FraudLabs Pro?

Yes. Allow read actions and deny writes in the FraudLabs Pro policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call FraudLabs Pro too?

Yes. The same FraudLabs Pro connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug FraudLabs Pro into your agent.

Your users connect FraudLabs Pro once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan