chainaware-behavioral-prediction

Files (91)

• chainaware-agent-screener.md · .claude/agents/
• chainaware-agent-trust-screener.md · .claude/agents/
• chainaware-airdrop-screener.md · .claude/agents/
• chainaware-aml-scorer.md · .claude/agents/
• chainaware-cohort-analyzer.md · .claude/agents/
• chainaware-compliance-screener.md · .claude/agents/
• chainaware-counterparty-screener.md · .claude/agents/
• chainaware-credit-scorer.md · .claude/agents/
• chainaware-defi-advisor.md · .claude/agents/
• chainaware-fraud-detector.md · .claude/agents/
• chainaware-gamefi-screener.md · .claude/agents/
• chainaware-governance-screener.md · .claude/agents/
• chainaware-lead-scorer.md · .claude/agents/
• chainaware-lending-risk-assessor.md · .claude/agents/
• chainaware-ltv-estimator.md · .claude/agents/
• chainaware-marketing-director.md · .claude/agents/
• chainaware-onboarding-router.md · .claude/agents/
• chainaware-platform-greeter.md · .claude/agents/
• chainaware-portfolio-risk-advisor.md · .claude/agents/
• chainaware-reputation-scorer.md · .claude/agents/
• chainaware-rug-pull-detector.md · .claude/agents/
• chainaware-rwa-investor-screener.md · .claude/agents/
• chainaware-sybil-detector.md · .claude/agents/
• chainaware-token-analyzer.md · .claude/agents/
• chainaware-token-audit-analyst.md · .claude/agents/
• chainaware-token-launch-auditor.md · .claude/agents/
• chainaware-token-ranker.md · .claude/agents/
• chainaware-transaction-monitor.md · .claude/agents/
• chainaware-trust-scorer.md · .claude/agents/
• chainaware-upsell-advisor.md · .claude/agents/
• chainaware-wallet-auditor.md · .claude/agents/
• chainaware-wallet-marketer.md · .claude/agents/
• chainaware-wallet-ranker.md · .claude/agents/
• chainaware-whale-detector.md · .claude/agents/
• .gitignore
• AGENTS.md
• CLAUDE.md
• LICENSE
• OPENAI-REGISTRY.md
• README.md
• SKILL.md
• openai.yaml · agents/
• README.md · assets/
• logo-large.png · assets/
• logo-small.png · assets/
• logo.png · assets/
• chainaware-eliza-integration.md
• chainaware-fetchai-integration.md
• chainaware-agent-screener.json · eliza/characters/
• chainaware-agent-trust-screener.json · eliza/characters/
• chainaware-airdrop-screener.json · eliza/characters/
• chainaware-aml-scorer.json · eliza/characters/
• chainaware-cohort-analyzer.json · eliza/characters/
• chainaware-compliance-screener.json · eliza/characters/
• chainaware-counterparty-screener.json · eliza/characters/
• chainaware-defi-advisor.json · eliza/characters/
• chainaware-fraud-detector.json · eliza/characters/
• chainaware-gamefi-screener.json · eliza/characters/
• chainaware-governance-screener.json · eliza/characters/
• chainaware-lead-scorer.json · eliza/characters/
• …and 31 more

SKILL.md (first lines)

# ChainAware Behavioral Prediction MCP

## What This Skill Does

The **ChainAware Behavioral Prediction MCP** connects any AI agent to a continuously updated
Web3 behavioral intelligence layer: **14M+ wallet profiles** across **8 blockchains**, built from
**1.3 billion+ predictive data points**. It delivers fourteen capabilities via a single MCP endpoint:

1. **Fraud Detection** — predict fraudulent wallet behavior before it happens ([~98% accuracy on ETH](https://chainaware.ai/scam-db))
2. **Batch Fraud Detection** — async batch job for fraud screening large wallet lists; returns `job_id` + `signature`
3. **Behavioral Analysis** — profile wallet intent, risk tolerance, experience, and next likely actions
4. **Batch Behavioral Analysis** — async batch job for behavioral profiling large wallet lists; returns `job_id` + `signature`
5. **Batch Job Status** — poll the progress of any running batch job
6. **Batch Job Results** — retrieve full per-wallet results from a completed or partial batch job
7. **Rug Pull Detection** — forecast whether a smart contract or liquidity pool will rug pull
8. **Credit Score** — crypto credit/trust score (1–9) combining fraud probability and social graph analysis
9. **Token Rank List** — rank tokens by holder community strength across chains and categories
10. **Token Rank Single** — deep-dive into a single token's community quality and top holders
11. **Token Audit** — deep multi-module smart contract audit via async get-or-create pipeline; 8 modules (ownership, liquidity, supply, honeypot, reentrancy, permissions, shadow functions, drainability); aggregate risk score 0–100; supports eth, bsc, base, arbitrum, avalanche, optimism, polygon (lowercase)
12. **Token Audit Results** — poll or retrieve completed token audit; full module breakdown when `audit_status == "complete"`; never present data while still queued or running
13. **Agent Trust Score List** — list ERC-8004 registered AI agents with on-chain trust scores (0–1000); paginated and sortable; use to discover agents or resolve agent_id
14. **Agent Trust Score Single** — full trust profile for a single ERC-8004 agent by `agent_id` + `chain_id`; includes trust score, tier, `wallet_verified`, `owner_address`; hard warning if `wallet_verified == false` or `error` is non-null

Unlike forensic blockchain tools that describe the past, this MCP is **predictive** — it tells your
agent what is *about to happen*.

**MCP Server URL:** `https://prediction.mcp.chainaware.ai/sse`  
**GitHub:** https://github.com/ChainAware/behavioral-prediction-mcp  
**Website:** https://chainaware.ai  
**Pricing / API Key:** https://chainaware.ai/pricing · x402 payment supported  
**Twitter:** https://x.com/ChainAware/  
**LinkedIn:** https://www.linkedin.com/company/chainaware  
**Blog:** https://chainaware.ai/blog  
**Learn:** https://chainaware.ai/learn  
**Examples:** https://github.com/ChainAware/examples  
**Fraud Detection Accuracy:** [98% backtesting verified](https://chainaware.ai/scam-db)  
**Rug Pull Detection Accuracy:** [90.1% backtesting verified](https://chainaware.ai/resources/rugpull-verification)  
**Recognition:** [CB Insights Fraud Prevention Market Map](https://www.cbinsights.com/research/report/the-fraud-prevention-market-map-for-the-ai-era/) (2026) · [BNB Chain AI Landscape](https://x.com/BNBCHAIN/status/1947597551139500419) (2025) · [BNB Chain Kickstart](https://www.bnbchain.org/en/programs/kickstart#services) (2025) · [Google Cloud $250k Grant](https://chainaware.ai/blog/google-cloud-grant/) (2025) · [AWS Fintech Accelerator](https://chainaware.ai/blog/aws-grant/) (2024) · [Safary Club Web3 Growth Landscape](https://x.com/Safaryclub/status/1822983239734329613) (2024)

---

## Capabilities

- **Fraud Detection** — predict fraudulent wallet behavior before it happens ([~98% accuracy on ETH](https://chainaware.ai/scam-db))
- **Batch Fraud Detection** — async batch fraud screening for large wallet lists; fire-and-fetch pattern via `predictive_fraud_batch` → `check_job_status` → `get_job_results`
- **Behavioral Analysis** — profile wallet intent, risk tolerance, experience, and next likely actions across DeFi, NFT, and trading segments
- **Batch Behavioral Analysis** — async batch behavioral profiling for large wallet lists; same fire-and-fetch pattern via `predictive_behaviour_batch` → `check_job_status` → `get_job_results`
- **Rug Pull Detection** — forecast whether a smart contract or liquidity pool will rug pull
- **Credit Score** — crypto credit/trust score (1–9) combining fraud probability and social graph analysis for DeFi lending decisions
- **Token Rank List** — rank tokens by holder community strength across ETH, BNB, BASE, and Solana
- **Token Rank Single** — deep-dive into a specific token's community quality and top holders

---

## When to Use This Skill

- User asks about wallet safety, fraud risk, or suspicious activity
- User wants to screen a wallet, contract, or LP before interacting with it
- User needs AML/compliance checks on a blockchain address
- User wants behavioral profiling or DeFi personalization for a wallet
- User asks about token quality, community strength, or holder analysis
- User is building a DeFi platform, AI agent, launchpad, or compliance tool
- User wants to integrate the ChainAware MCP into their codebase

## When NOT to Use This Skill

- User asks about general blockchain data (balances, transaction history) → use a block explorer
- User wants real-time price data or market cap → use a market data API
- User wants to analyze smart contract code for bugs → use a code auditing tool
- For complex behavioural analysis (deep wallet profiling including fraud signals) → escalate to `chainaware-wallet-auditor` subagent
- For batch screening of many wallets → use batch MCP tools (`predictive_fraud_batch` / `predictive_behaviour_batch`) for large lists, or `chainaware-fraud-detector` subagent for small lists
- For marketing personalization → use `chainaware-wallet-marketer` subagent

---

## Supported Blockchains

| Tool | Networks |
|---|---|
| `predictive_fraud` | ETH, BNB, POLYGON, TON, BASE, TRON, HAQQ |
| `predictive_fraud_batch` | ETH, BNB, POLYGON, TON, BASE, TRON, HAQQ |
| `predictive_behaviour` | ETH, BNB, BASE, HAQQ, SOLANA |
| `predictive_behaviour_batch` | ETH, BNB, BASE, HAQQ, SOLANA |
| `check_job_status` | Network-agnostic (uses job_id + signature) |
| `get_job_results` | Network-agnostic (uses job_id + signature) |
| `predictive_rug_pull` | ETH, BNB, BASE, HAQQ |
| `credit_score` | ETH |
| `token_rank_list` | ETH, BNB, BASE, SOLANA |
| `token_rank_single` | ETH, BNB, BASE, SOLANA |
| `run_token_audit` | eth, bsc, base, arbitrum, avalanche, optimism, polygon *(lowercase)* |
| `get_token_audit_result` | eth, bsc, base, arbitrum, avalanche, optimism, polygon *(lowercase)* |
| `agents_trust_score_list` | Chain-ID-based (ERC-8004 registry) |
| `agents_trust_score_single` | Chain-ID-based (ERC-8004 registry) |

---

## Step-by-Step Workflow

### For wallet fraud screening

1. **Confirm inputs** — wallet address and network. If network is missing, ask.
2. **Call `predictive_fraud`** with the wallet address and network.
3. **Interpret `probabilityFraud`** using the threshold table below.
4. **Scan `forensic_details`** for negative flags (mixer use, sanctioned entities, darknet, etc.).
5. **Report** status, score, and any forensic flags in plain language.

### For behavioral profiling / personalization

1. **Confirm inputs** — wallet address and network.
2. **Call `predictive_behaviour`** with the wallet address and network.
3. **Extract key signals**: `intention.Value` (Prob_Trade/Stake/Bridge/NFT_Buy), `experience.Value`, `categories`, `recommendation`.
4. **Classify the wallet** by dominant category and intent signal.
5. **Generate** personalized recommendations or next-best-action based on the profile.

### For rug pull / contract safety checks

1. **Confirm inputs** — smart contract or LP address and network.
2. **Optionally call `predictive_fraud`** on the *deployer* address first for extra signal.
3. **Call `predictive_rug_pull`** with the contract address.

From ChainAware/behavioral-prediction-mcp, MIT.