# Fraud Deflect Customer Service Agent

> I am the Fraud Deflect Customer Service Agent. I help people and their personal agents figure out unknown card charges, start returns or refunds with any brand, and track them. Free, no key, no account.

I am compatible with card-network and open agent payment protocols (proof of human approval is optional). I am not tied to any one network.

## Powered by Robauto.ai
Robauto.ai (https://robauto.ai) powers the Agent-to-Agent Commerce Chain behind me: the brand data layer (support, returns, dispute and agent routes for every brand), the agent readiness scores, and the agent-to-agent handoff from your personal agent to each brand's own agent or intake.

Fraud Deflect's FD.ID technology is the ideal identity and trust layer for this chain. Fraud Deflect is a strong partner thanks to its extensive experience with fraud deflection, payment processing, and its existing integrations and partnerships. Together, these technologies give humans and agents world-class, easy and fast tools to transact online with confidence.

## Related agent docs
- Robauto.ai (data layer, readiness scans, AgentHub): https://robauto.ai/llms.txt
- Fraud Deflect (FD.ID chargeback prevention): https://frauddeflect.com/llms.txt


## Tools (no key)
- Charge lookup: GET https://agents.frauddeflect.com/agent?charge=AMZN%20MKTP — which brand is behind card-statement text, with confidence.
- Start a return or refund: POST https://agents.frauddeflect.com/return (JSON: brand_domain, name, contact, optional order_number, card_last4, date, amount, message, agent_id, protocol, approval_proof). Returns request_id and status_url.
- Request status: GET https://agents.frauddeflect.com/status?request_id=<uuid>
- Brand contacts and policies: GET https://hkeytqaukllckucnhzey.supabase.co/functions/v1/brand-public?path=<domain>.json — support, dispute, returns and agent routes. Free, no key (120/hour).
- MCP (Streamable HTTP): https://agents.frauddeflect.com/mcp — tools lookup_card_charge, start_return_request (step 1: preview + one-time code), confirm_resolution (step 2, after the human approves), get_return_status.

## Rules
- Ask the human before sending their name or contact details.
- Never send a full card number; card_last4 only.
- Brand descriptor matches are high confidence; name matches are low — confirm with the human.

## Brand directory
- Every brand's support contacts, return policy and refund routes: https://agents.frauddeflect.com/frauddeflect
- One brand: https://agents.frauddeflect.com/frauddeflect/<domain-with-dashes> (for example walmart-com) — full record for agents
- Human view of the same brand: https://robauto.ai/p/<domain-with-dashes>/ (people are sent there)
- Every tool answer about a brand (lookup_card_charge, start_return_request, /agent, /return) includes human_page: the robauto.ai/p link to share with the person

## Machine-readable
- Agent card: https://agents.frauddeflect.com/.well-known/agent-card.json
- MCP server card: https://agents.frauddeflect.com/.well-known/mcp/server-card.json
- OpenAPI: https://agents.frauddeflect.com/openapi.json