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.
git clone --depth 1 https://github.com/ChainAware/behavioral-prediction-mcpWrote 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.
[](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-fraud-detector)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Extract the wallet address and network from the user's message
- Clarify network if ambiguous — ask once, don't guess for high-stakes checks
- Call
predictive_fraudwithapiKey,network,walletAddress - Return a clear, structured verdict (see output format below)
- 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 |
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.
- 8d ago First seen · 201 lines · 153 tokens per session scan A f3e1ae84d353
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.
Other agents, from other repositories
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
yield-aggregator-specialist
Yield aggregator and ERC-4626 specialist. Yearn V3, Beefy, Sommelier, MetaMorpho, custom vaults with strategies. Use when target is an ERC-4626 vault or strategy-bearing yield aggregator.
attacker
Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.