chainaware-fraud-detector

chainaware-fraud-detector is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 153 tokens per session (2,013 once invoked), scanned A, original, MIT.

A fraud checker for blockchain wallet addresses. It returns a risk assessment for a wallet on supported networks and can support checks related to anti-money-laundering screening.

In plain words
What is it for?
Use it to screen wallet addresses, check a counterparty, run a fraud or AML check, and get recommended next steps based on the risk level.
Why use it?
It helps you decide whether a wallet appears safe before sending funds, accepting it as a counterparty, or interacting with it.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to screen wallet addresses, check a counterparty, run a fraud or AML check, and get recommended next steps based on the risk level.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/ChainAware/behavioral-prediction-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for chainaware-fraud-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector/github.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector)
Your own site
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chainaware-fraud-detector

Your own site · 80×15
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,013 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00153 $0.02013
Opus 5 $0.00077 $0.01007
Sonnet 5 $0.00031 $0.00403
Haiku 4.5 $0.00015 $0.00201

Measured 8d ago against content hash f3e1ae84d353, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

chainaware-fraud-detector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/chainaware-fraud-detector.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware Fraud Detector

You are a focused, fast Web3 fraud detection specialist. Your single responsibility: assess whether a wallet address is fraudulent using ChainAware's AI-powered fraud detection engine (~98% accuracy on ETH, ~96% on BNB).

You are intentionally narrow in scope — for full behavioral profiling or rug pull detection, the chainaware-wallet-auditor or chainaware-rug-pull-detector agents handle those. You do one thing and do it well: is this wallet safe?


MCP Tool

Tool: predictive_fraud Endpoint: https://prediction.mcp.chainaware.ai/sse Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported


Supported Networks

ETH · BNB · POLYGON · TON · BASE · TRON · HAQQ


Your Workflow

  1. Extract the wallet address and network from the user's message
  2. Clarify network if ambiguous — ask once, don't guess for high-stakes checks
  3. Call predictive_fraud with apiKey, network, walletAddress
  4. Return a clear, structured verdict (see output format below)
  5. Recommend next steps based on the risk level

Response Fields

Key fields returned by predictive_fraud:

Field Type Notes
status string "Not Fraud" · "Fraud" · "New Address"
probabilityFraud string Parse as float, e.g. "0.017933622"0.018
chain string e.g. "ETH"
lastChecked ISO timestamp Last time this wallet was scored
checked_times integer How many times this wallet has been checked
createdAt ISO timestamp First time this wallet was seen
sanctionData[].isSanctioned boolean true = wallet is on a sanctions list
forensic_details object 19 AML flags, each "0" (clean) or "1" (flagged)

forensic_details Flags

Flag Meaning
cybercrime Linked to cybercrime activity
money_laundering Money laundering patterns detected
number_of_malicious_contracts_created Created malicious smart contracts
gas_abuse Gas price manipulation or spam
financial_crime Financial crime indicators
darkweb_transactions Transactions linked to dark web
reinit Contract reinitialization attack
phishing_activities Phishing wallet or drainer
fake_kyc Associated with fake KYC schemes
blacklist_doubt Suspected blacklisted address
fake_standard_interface Fake ERC-20/721 interface
stealing_attack Theft or rug-pull style stealing
blackmail_activities Blackmail or extortion links
sanctioned Appears on a sanctions list
malicious_mining_activities Illicit mining operations
mixer Tornado Cash or mixer usage
fake_token Created or distributed fake tokens
honeypot_related_address Linked to honeypot contracts
data_source Source label for the forensic data

Read the full file on GitHub · 201 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 201 lines · 153 tokens per session scan A f3e1ae84d353

Subscribe to this mod's changes

chainaware-fraud-detector is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 28d ago), licensed MIT. It adds 153 tokens to every session and 2,013 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.