# BRAINIAC Fraud & Transaction Security

> BRAINIAC Fraud & Transaction Security is a paid MCP server for security. Pay-per-call fraud and transaction security API for AI agents, paid in USDC via x402. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API
- **Website:** https://www.brainiac.software
- **MCP Registry name:** software.brainiac/fraud-signals
- **Categories:** [security](https://ai-powered.com/categories/security), [smart contract security](https://ai-powered.com/categories/smart-contract-security)
- **Listing updated:** 2026-11-20

## About

The MCP server exposes a fraud and transaction security API that AI agents can call on demand. Each tool call is priced in a fixed USDC amount on the Base network, and requests without payment receive an HTTP 402 response, so access is settled per call rather than through a subscription.

The registry entry describes the server as a paid fraud and transaction security API, and the vendor site positions the wider service around sanctions screening, compliance checks, token security and Base onchain data. The site states there is no account to create, which suits agents that need to pay and act without a human sign-up step.

It is aimed at developers and autonomous agents that handle payments or onchain transactions and need a risk check before proceeding.

## Features

- **Pay-per-call pricing:** Each request is charged a fixed USDC amount on Base, with no account or subscription required.
- **x402 payment flow:** Unpaid tool calls return HTTP 402, prompting the client to complete payment before receiving a result.
- **Streamable HTTP transport:** The MCP server is reachable over streamable HTTP at the vendor's hosted endpoint.
- **Sanctions and compliance checks:** The vendor site lists sanctions and compliance screening among the available API categories.
- **Onchain data access:** The vendor site mentions Base onchain data alongside its security APIs.

## Good for

- Screen counterparties against sanctions lists before an agent sends a payment
- Run a risk check on a token before an agent swaps or holds it
- Add transaction security checks to an autonomous trading or payment workflow
- Pull Base onchain data for compliance review without setting up accounts

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http fraud-signals https://www.brainiac.software/mcp/fraud-signals
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://www.brainiac.software/mcp/fraud-signals
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "fraud-signals": {
      "url": "https://www.brainiac.software/mcp/fraud-signals"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "fraud-signals": {
      "type": "http",
      "url": "https://www.brainiac.software/mcp/fraud-signals"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "fraud-signals": {
      "serverUrl": "https://www.brainiac.software/mcp/fraud-signals"
    }
  }
}
```

### Grok Bot (Grok Bot desktop app → Connect apps → Add a custom connector)

```sh
https://www.brainiac.software/mcp/fraud-signals
```

Enter a Name (for example "BRAINIAC Fraud & Transaction Security"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "fraud-signals": {
      "type": "http",
      "url": "https://www.brainiac.software/mcp/fraud-signals"
    }
  }
}
```

## Tools

All 8 tools say they're read-only. From the server's own tool annotations; not verified by us.

- `fraud-signals_payment-fraud-pattern-detect` (says read-only): Detect suspicious combinations of caller-supplied payment events (declines-then-success, instrument churn, billing/shipping mismatch) before you accept, pay, or refund a transaction. Anomalies are not confirmed fraud. Call with optional text, json, csv, file, files, payments and others. HTTP 200 with status complete, partial, or failed is charged at the full listed price. HTTP 4xx/5xx are not char
- `fraud-signals_transaction-velocity-analyze` (says read-only): Identify abnormal transaction frequency and amount velocity from caller-supplied histories before you accept, pay, or refund a transaction. Velocity spikes alone are never labeled confirmed fraud. Call with optional text, json, csv, file, files, payments and others. Returns checkedAt, itemCount, windowMinutes, items, paidProviderUsed, apiKeyRequired, paymentProcessorConnected. HTTP 200 with status
- `fraud-signals_synthetic-identity-signal-detect` (says read-only): Identify inconsistencies in caller-supplied identity records (sparse profiles, age/postal mismatches, shared contacts) before you accept, pay, or refund a transaction. Personal data is masked in responses. Call with optional text, json, csv, file, files, payments and others. Returns checkedAt, itemCount, items, paidProviderUsed, apiKeyRequired, paymentProcessorConnected. HTTP 200 with status compl
- `fraud-signals_invoice-fraud-signal-detect` (says read-only): Detect potentially manipulated invoices from caller-supplied invoice exports (duplicate numbers, tax anomalies, missing PO) before you accept, pay, or refund a transaction. Not confirmed fraud. Call with optional text, json, csv, file, files, payments and others. Returns checkedAt, itemCount, items, paidProviderUsed, apiKeyRequired, paymentProcessorConnected. HTTP 200 with status complete, partial
- `fraud-signals_supplier-bank-change-risk` (says read-only): Identify suspicious supplier bank-detail changes near invoice timing from caller-supplied records before you accept, pay, or refund a transaction. Bank values are last4-masked. Call with optional text, json, csv, file, files, payments and others. Returns checkedAt, itemCount, items, paidProviderUsed, apiKeyRequired, paymentProcessorConnected, financialAccountAccessed. HTTP 200 with status complete
- `fraud-signals_refund-abuse-pattern-detect` (says read-only): Detect abnormal refund frequency and amount ratios from caller-supplied payment histories before you accept, pay, or refund a transaction. Refund rate alone is not confirmed fraud. Call with optional text, json, csv, file, files, payments and others. Returns checkedAt, itemCount, windowDays, items, paidProviderUsed, apiKeyRequired, paymentProcessorConnected. HTTP 200 with status complete, partial,
- `fraud-signals_chargeback-pattern-analyze` (says read-only): Analyze recurring chargeback/dispute patterns from caller-supplied payment records before you accept, pay, or refund a transaction. Elevated rates are indicators, not confirmed fraud. Call with optional text, json, csv, file, files, payments and others. Returns checkedAt, itemCount, windowDays, items, paidProviderUsed, apiKeyRequired, paymentProcessorConnected. HTTP 200 with status complete, parti
- `fraud-signals_multi-account-fraud-cluster` (says read-only): Group potentially related accounts using deterministic overlap of caller-supplied emails, phones, devices, IPs, and payment-instrument last4 values before you accept, pay, or refund a transaction. Linkage is not confirmed fraud. Call with optional text, json, csv, file, files, payments and others. HTTP 200 with status complete, partial, or failed is charged at the full listed price. HTTP 4xx/5xx a

## FAQ

### Do I need an account to use BRAINIAC Fraud & Transaction Security?

The vendor site says there is no account to set up; you pay a fixed USDC price on Base for each result.

### What happens if a call is not paid?

The registry entry says unpaid tool calls return a 402 response.

### How is BRAINIAC Fraud & Transaction Security connected to an AI client?

The registry entry lists a streamable HTTP remote at https://www.brainiac.software/mcp/fraud-signals.

### How do I add BRAINIAC Fraud & Transaction Security to Claude Code?

Run this command in your terminal: claude mcp add --transport http fraud-signals https://www.brainiac.software/mcp/fraud-signals

### What are the best alternatives to BRAINIAC Fraud & Transaction Security?

The closest alternatives to BRAINIAC Fraud & Transaction Security are BRAINIAC Application & Pipeline Security Checks, BRAINIAC Brand Protection, BRAINIAC Ad Fraud Intelligence, BRAINIAC Agent Execution Contract Intelligence and BRAINIAC API catalog.

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Status and tools: checked automatically by AIPoweredBot on 21 November 2026.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [BRAINIAC Application & Pipeline Security Checks](https://ai-powered.com/mcp/brainiac-application-and-pipeline-security-checks): BRAINIAC Application & Pipeline Security Checks is a paid MCP server for security.
- [BRAINIAC Brand Protection](https://ai-powered.com/mcp/brainiac-brand-protection): BRAINIAC Brand Protection is a paid MCP server for security.
- [BRAINIAC Ad Fraud Intelligence](https://ai-powered.com/mcp/brainiac-ad-fraud-intelligence): BRAINIAC Ad Fraud Intelligence is a paid MCP server for marketing and seo.
- [BRAINIAC Agent Execution Contract Intelligence](https://ai-powered.com/mcp/brainiac-agent-execution-contract-intelligence): BRAINIAC Agent Execution Contract Intelligence is a paid MCP server for legal and government.
- [BRAINIAC API catalog](https://ai-powered.com/mcp/brainiac-api-catalog): BRAINIAC API catalog is a paid MCP server for agent tooling.
- [BRAINIAC Base Chain Data](https://ai-powered.com/mcp/brainiac-base-chain-data): BRAINIAC Base Chain Data is a paid MCP server for crypto and web3.
- [BRAINIAC Account Abstraction](https://ai-powered.com/mcp/brainiac-account-abstraction): BRAINIAC Account Abstraction is a paid MCP server for crypto and web3.
- [BRAINIAC Appointment Intelligence](https://ai-powered.com/mcp/brainiac-appointment-intelligence): BRAINIAC Appointment Intelligence is a paid MCP server for agent tooling.

---
Source: https://ai-powered.com/mcp/brainiac-fraud-and-transaction-security
