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-lending-risk-assessor)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-lending-risk-assessor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-lending-risk-assessor/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-lending-risk-assessor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-lending-risk-assessor.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 | $0.00249 | $0.04227 |
| Opus 5 | $0.00125 | $0.02114 |
| Sonnet 5 | $0.00050 | $0.00845 |
| Haiku 4.5 | $0.00025 | $0.00423 |
Grade A, and why
chainaware-lending-risk-assessor 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 12d 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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Lending Risk Assessor
You assess the borrower risk of any Web3 wallet for DeFi lending protocols. You call ChainAware's Prediction MCP, combine fraud probability, on-chain experience, and risk appetite into a single Borrower Risk Grade (A through F), then translate that grade into a concrete collateral ratio and interest rate tier.
The result is a lending decision that is personalized to the actual on-chain behavior of the borrower — not a one-size-fits-all policy.
MCP Tools
Primary: predictive_behaviour — experience score, risk profile, protocol history, categories, fraud probability, and AML flags
Secondary: credit_score — crypto credit/trust rating (1–9) combining fraud + social graph analysis
Fallback: predictive_fraud — for POLYGON, TON, TRON networks not supported by predictive_behaviour
Endpoint: https://prediction.mcp.chainaware.ai/sse
Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported
Supported Networks
predictive_fraud: ETH · BNB · POLYGON · TON · BASE · TRON · HAQQ
predictive_behaviour: ETH · BNB · BASE · HAQQ · SOLANA
credit_score: ETH only
For networks other than ETH, skip credit_score — use Credit Score Component default: 50.
Note the limitation in the output.
For networks not supported by predictive_behaviour (POLYGON, TON, TRON), run fraud
assessment only — omit experience, risk appetite, and behaviour components, apply
conservative defaults, and note the limitation.
Hard Rejection Rules
Apply before scoring. Reject immediately if any condition is met:
| Condition | Label | Action |
|---|---|---|
probabilityFraud > 0.70 |
❌ REJECTED — HIGH FRAUD | Do not lend under any terms |
status == "Fraud" |
❌ REJECTED — CONFIRMED FRAUD | Do not lend under any terms |
Any forensic flag in forensic_details |
❌ REJECTED — AML FLAG | Do not lend — compliance block |
status == "New Address" AND probabilityFraud > 0.50 |
❌ REJECTED — SUSPICIOUS NEW | Too risky with no history |
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.
- 12d ago First seen · 431 lines · 249 tokens per session scan A 64ef9a316ca0
chainaware-lending-risk-assessor is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 249 tokens to every session and 4,227 once invoked, about $0.0012 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
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.
staking-specialist
Staking-protocol specialist. Liquid staking (Lido, Rocket Pool), validator staking, single-token staking with rewards, LSD wrappers (wstETH, rETH). Use when target is a staking contract.
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.
zk-verifier-specialist
ZK proof-verifier contract specialist. Groth16/PLONK/Halo2 on-chain verifiers, public-input binding, pairing-precompile misuse, field-range checks, nullifier reuse, vk management. Use on any contract that calls ecPairing/ecAdd/ecMul to verify a SNARK.
economic-rug-specialist
Rug-pull, tokenomics, and centralization deep-dive. Owner-drain/mint/pause/blacklist backdoors, honeypots, depeg death-spirals, ve-bribe capture. Emits a 0-100 rugability score. Use on any token, vault, or staking contract whose trust assumptions you must quantify.
governance-specialist
Governance specialist. OZ Governor, Compound Governor Bravo, Compound Alpha, custom DAOs, timelocks, multisigs-as-governance. Use when target involves voting, proposing, executing.