For AI Agents¶
ChainAware's Behavioral Prediction MCP exposes the full power of the ChainAware AI platform as a set of Claude Code subagents. Any Claude Code environment — an IDE, a terminal, a CI pipeline, or an AI product — can install these agents and immediately gain predictive blockchain intelligence without writing a single line of API integration code.
Subagents
MCP Tools
Blockchains
Wallet Profiles
What Is the Behavioral Prediction MCP?¶
The ChainAware Behavioral Prediction MCP is a Model Context Protocol server that exposes six core prediction tools:
| Tool | What It Does |
|---|---|
predictive_fraud |
Scores a wallet address for fraud risk (0–1) |
predictive_behaviour |
Predicts on-chain behavioural patterns for a wallet |
predictive_rug_pull |
Assesses rug pull risk for a token address |
credit_score |
AI-driven crypto trust score (1–9) for lending and credit decisions |
token_rank_list |
Returns ranked token lists by risk and quality |
token_rank_single |
Detailed analysis of a single token |
The 31 subagents in this repository are pre-built Claude Code agents that wrap these tools with focused prompts, role definitions, and decision logic — so you get expert blockchain AI behaviour out of the box.
Quick Setup¶
Step 1 — Get an API key
Contact ChainAware at chainaware.ai/support to receive your API key.
Step 2 — Register the MCP server in Claude Code
claude mcp add --transport sse chainaware-behavioral-prediction \
https://prediction.mcp.chainaware.ai/sse \
--header "X-API-Key: YOUR_API_KEY"
Step 3 — Install the subagents
Clone the repository and copy the agent files to your project:
git clone https://github.com/ChainAware/behavioral-prediction-mcp.git
cp behavioral-prediction-mcp/.claude/agents/*.md .claude/agents/
That's it. The agents are now available in any Claude Code session in that project directory. Invoke them with claude --agent chainaware-fraud-detector or trigger them from within Claude Code using @chainaware-fraud-detector.
Agent Categories¶
The 31 agents are organised into five functional groups:
🔐 Security & Fraud
Real-time fraud detection, rug pull screening, wallet auditing, AML scoring, and compliance screening.
8 agents
View Security Agents →⚠️ Risk & Safety
Counterparty screening, lending risk, token launch auditing, portfolio risk advisory, and RWA screening.
6 agents
View Risk Agents →📈 Growth & Marketing
Onboarding routing, whale detection, DeFi advisory, airdrop screening, cohort analysis, lead scoring, and wallet marketing.
10 agents
View Growth Agents →🏆 Rankings & Tokens
Wallet ranking by behaviour, token ranking by risk, and deep token analysis combining rank and fraud signals.
3 agents
View Token Agents →🎮 Specialised
GameFi player screening and DAO governance participation screening — purpose-built for specific Web3 verticals.
2 agents
View Specialised Agents →Get Started
Questions about the MCP, API keys, or enterprise deployment? The ChainAware team can help.
Contact ChainAware →View on GitHub →
Full Agent List¶
| Agent | Category | Tools Used |
|---|---|---|
| chainaware-fraud-detector | Security | predictive_fraud |
| chainaware-rug-pull-detector | Security | predictive_rug_pull, predictive_fraud |
| chainaware-wallet-auditor | Security | predictive_fraud, predictive_behaviour, predictive_rug_pull |
| chainaware-trust-scorer | Security | predictive_fraud |
| chainaware-aml-scorer | Security | predictive_fraud |
| chainaware-reputation-scorer | Security | predictive_behaviour, predictive_fraud |
| chainaware-compliance-screener | Security | predictive_fraud |
| chainaware-transaction-monitor | Security | predictive_fraud, predictive_rug_pull, predictive_behaviour |
| chainaware-counterparty-screener | Risk | predictive_fraud, predictive_behaviour |
| chainaware-lending-risk-assessor | Risk | predictive_behaviour, predictive_fraud |
| chainaware-token-launch-auditor | Risk | predictive_rug_pull, predictive_fraud, predictive_behaviour |
| chainaware-agent-screener | Risk | predictive_fraud, predictive_behaviour |
| chainaware-portfolio-risk-advisor | Risk | predictive_rug_pull, token_rank_single |
| chainaware-rwa-investor-screener | Risk | predictive_fraud, predictive_behaviour |
| chainaware-onboarding-router | Growth | predictive_behaviour, predictive_fraud |
| chainaware-whale-detector | Growth | predictive_behaviour, predictive_fraud |
| chainaware-defi-advisor | Growth | predictive_behaviour, predictive_fraud |
| chainaware-airdrop-screener | Growth | predictive_behaviour, predictive_fraud |
| chainaware-cohort-analyzer | Growth | predictive_behaviour, predictive_fraud |
| chainaware-lead-scorer | Growth | predictive_behaviour, predictive_fraud |
| chainaware-upsell-advisor | Growth | predictive_behaviour, predictive_fraud |
| chainaware-platform-greeter | Growth | predictive_behaviour, predictive_fraud |
| chainaware-marketing-director | Growth | predictive_fraud |
| chainaware-wallet-marketer | Growth | predictive_behaviour, predictive_fraud |
| chainaware-wallet-ranker | Tokens | predictive_behaviour |
| chainaware-token-ranker | Tokens | token_rank_list |
| chainaware-token-analyzer | Tokens | token_rank_single, predictive_fraud |
| chainaware-gamefi-screener | Specialised | predictive_behaviour, predictive_fraud |
| chainaware-governance-screener | Specialised | predictive_behaviour, predictive_fraud |
Get an API key and start using the ChainAware MCP in minutes.
Get API Access → GitHub Repository →
Further Reading¶
- 12 Blockchain Capabilities Any AI Agent Can Use — MCP Integration Guide — all 12 agent capabilities with MCP setup for Claude, ChatGPT, Cursor, and multi-agent architectures
- Prediction MCP for AI Agents: Personalize Decisions from Wallet Behavior — full MCP integration guide with code examples
- Top 5 Ways Prediction MCP Will Turbocharge Your DeFi Platform — lending, DEX, launchpad, governance, and personalization use cases
- Why Personalization Is the Next Big Thing for AI Agents — the case for wallet-level personalization in Web3
- The Web3 Agentic Economy: How AI Agents Are Replacing Human Teams in DeFi — how autonomous AI agents are taking over DeFi operations and decision-making