Every AI agent needs tools. A financial advisor agent needs market data. A compliance agent needs regulatory screening. A marketing bot needs audience intelligence. Until now, blockchain intelligence — one of the richest behavioral data sources in the world — has been locked behind complex APIs that require deep crypto expertise to use.

That changes with Model Context Protocol (MCP).

ChainAware has published 12 open-source, pre-built agent definitions on GitHub that give any AI agent — Claude, GPT, or custom LLM — instant access to 14 million+ wallet behavioral profiles, 98% accurate fraud prediction, real-time AML screening, token holder analysis, and more. No crypto knowledge required. No custom integration work. Just clone, configure your API key, and your agent gains blockchain superpowers.

This guide covers all 12 agents, explains the MCP architecture in plain language, shows real-world multi-agent scenarios, and walks you through integration step by step. Whether you’re building financial compliance tools, investment research systems, or growth automation, these blockchain capabilities are now one configuration file away.

In This Guide

1. What Is MCP? (Plain Language Explanation)
2. Why MCP vs Direct API Integration
3. Architecture Overview
4. All 12 ChainAware MCP Agents Explained
5. 3 Multi-Agent Scenarios
6. Step-by-Step Integration Guide
7. Use Cases by Domain
8. Frequently Asked Questions

What Is MCP? (Plain Language Explanation)

MCP stands for Model Context Protocol — an open standard introduced by Anthropic in late 2024 that defines how AI agents communicate with external tools and data sources. Think of it as USB-C for AI agents: a single, universal connector that lets any compatible AI system plug into any compatible tool — without custom integration work for each pairing.

Before MCP, connecting an AI agent to a database or API required: writing custom function-calling code for each tool, maintaining separate API clients per service, rebuilding integrations whenever tool interfaces changed, and training agents specifically on each tool’s schema.

With MCP, tool providers (like ChainAware) publish a standardized server definition. Any MCP-compatible AI agent — Claude, GPT, open-source LLMs — can automatically discover, understand, and call that tool using natural language. The agent figures out when and how to call the tool based on the task at hand.

According to the official MCP documentation, the protocol is designed to give AI models “a standardized way to access context from tools, files, databases, and APIs.” In practice, this means your compliance agent can call a blockchain AML screening tool the same way it calls a sanctions database — without any extra integration work.

MCP vs Function Calling vs RAG

MCP shines in multi-agent systems where different agents need to share tools, or where a single agent needs to orchestrate calls across many data sources dynamically.

Why MCP vs Direct API Integration

If ChainAware already has a REST API, why use MCP at all? The answer is about agent-native design versus developer-first design.

A traditional REST API is designed for developers: endpoints, authentication headers, JSON schemas, documentation pages. Your AI agent can call it — but you need to write wrapper code, handle errors, parse responses, and teach the agent when and why to make each call.

An MCP server is designed for agents: the capability description, input schema, and expected output are all defined in a format that LLMs natively understand. The agent reads the tool definition and autonomously decides when to invoke it based on the task context.

Concrete advantages of MCP over direct API:

• Zero integration boilerplate — no API client code to write or maintain
• Autonomous tool selection — agent decides which tool to call, not your code
• Natural language invocation — “check if this wallet is safe” instead of constructing request objects
• Composable with other MCP tools — chain ChainAware calls with database queries, web searches, Slack notifications
• Works across LLM providers — same agent definition works with Claude, GPT, and open-source models
• Maintained by tool provider — when ChainAware updates its capabilities, the MCP definition updates, not your code

According to research from the Anthropic AI safety and alignment team on building effective agents, the most reliable agentic systems use well-defined tool interfaces that agents can understand and invoke without ambiguity. MCP is that interface.

Clone GitHub Repo

Get MCP API Key

Architecture Overview

Understanding how ChainAware MCP fits into an AI agent architecture helps clarify what you’re building. The flow is simple: your agent receives a task, identifies it needs blockchain intelligence, calls the appropriate ChainAware MCP tool in natural language, receives structured results, and incorporates them into its response or next action. The agent never needs to know about REST endpoints, authentication headers, or JSON schemas — MCP handles that layer.

┌─────────────────────────────────────────────────────────┐
│                    Your AI Agent                        │
│   (Claude / GPT / Custom LLM)                          │
│                                                         │
│  "Analyze this wallet before approving the transfer"    │
└──────────────────────┬──────────────────────────────┘
                       │ MCP Protocol
                       ▼
┌─────────────────────────────────────────────────────────┐
│              ChainAware MCP Server                      │
│                                                         │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐  │
│  │fraud-detector│  │  aml-scorer  │  │wallet-ranker │  │
│  └──────────────┘  └──────────────┘  └──────────────┘  │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐  │
│  │token-ranker  │  │trust-scorer  │  │whale-detector│  │
│  └──────────────┘  └──────────────┘  └──────────────┘  │
│               + 6 more agents...                        │
└──────────────────────┬──────────────────────────────┘
                       │ API calls
                       ▼
┌─────────────────────────────────────────────────────────┐
│           ChainAware Prediction Engine                  │
│                                                         │
│  14M+ wallets · 8 blockchains · 98% accuracy           │
│  ML models · Graph neural networks · Real-time data    │
└─────────────────────────────────────────────────────────┘

Each of the 12 agent definition files in the GitHub repository contains the tool description, capability scope, and usage examples that allow any compatible LLM to understand and invoke the capability correctly.

All 12 ChainAware MCP Agents Explained

Each agent below corresponds to a file in the /.claude/agents/ directory. Every agent works with MCP-compatible AI systems (Claude, GPT, custom LLMs) and requires an active ChainAware MCP subscription at chainaware.ai/mcp.

1. fraud-detector

GitHub: chainaware-fraud-detector.md

What it does: Evaluates any wallet address for fraud probability using ChainAware’s ML models trained on 14M+ wallets. Returns a trust score (0–100%), behavioral red flags, mixer interactions, network connections to known fraud addresses, and an overall fraud risk classification. This is ChainAware’s flagship capability — the engine that achieves 98% prediction accuracy by analyzing behavioral patterns rather than just blocklist matching.

Who needs it: Payment processors that need to screen crypto payees before releasing funds. DeFi protocol operators deciding whether to allow large withdrawals. Exchange compliance teams reviewing high-value accounts. Insurance underwriters assessing crypto custody risk. Lending platforms evaluating borrower creditworthiness in Web3.

Real-world integration example: An agent prompt like “A user wants to withdraw $85,000 from our DeFi protocol to wallet 0x4a2b…c8f1. Before approving, run a full fraud assessment and tell me if this transaction is safe to process” — the agent calls fraud-detector, receives the trust score and risk factors, and either auto-approves or flags for human review — all without the developer writing a single API call. See the complete guide: ChainAware Fraud Detector Guide.

2. rug-pull-detector

GitHub: chainaware-rug-pull-detector.md

What it does: Analyzes a token or project wallet for rug pull indicators — behaviors that signal the founders or team intend to abandon the project and exit with investor funds. Detection signals include: treasury wallet concentration, team allocation patterns, liquidity lock status, developer wallet interaction history, sudden large transfer preparation, and similarity to historical rug pull behavioral signatures in the training dataset.

Who needs it: Investment research agents evaluating new DeFi projects. DAO governance bots assessing partnership proposals. Token launch platforms conducting pre-listing due diligence. Institutional crypto fund managers screening emerging positions. News and analytics platforms that flag suspicious token activity for their users.

Real-world integration example: “A new DeFi yield protocol launched 3 weeks ago and is offering 800% APY. The contract address is 0x9c3d…f2a7. Assess the rug pull risk before we recommend it to our users.” The agent calls rug-pull-detector, cross-references the project wallet against historical rug pull patterns, and returns a risk classification with the specific behavioral signals driving the assessment.

3. aml-scorer

GitHub: chainaware-aml-scorer.md

What it does: Runs comprehensive Anti-Money Laundering screening on a wallet address. Returns sanctions list status (OFAC SDN and equivalents), mixer/tumbler interaction history, connections to known illicit addresses, geographic risk indicators, transaction structuring patterns, and an overall AML risk score. Designed to meet regulatory requirements for VASP compliance under FATF Recommendation 16 and regional equivalents.

Who needs it: Any compliance agent operating in regulated financial environments. Banks integrating crypto payment rails. Exchanges required to file SARs. Fintech platforms offering crypto on/off ramps. Legal and audit firms conducting blockchain forensics. Corporate treasury teams accepting crypto payments. See our complete Blockchain Compliance Guide for regulatory context.

Real-world integration example: “New corporate client wants to pay our invoice in USDC from wallet 0x7b1e…d4c9. Run a full AML check and tell me if we can legally accept this payment without filing a SAR.”

4. wallet-ranker

GitHub: chainaware-wallet-ranker.md

What it does: Generates a comprehensive Wallet Rank score (0–100) for any address, consolidating 10 behavioral parameters: risk willingness, experience level, risk capability, predicted trust, intentions, transaction categories, protocol diversity, AML status, wallet age, and balance. The rank represents overall wallet quality — higher scores indicate sophisticated, trustworthy users with significant Web3 activity. Full methodology: ChainAware Wallet Rank Guide.

Who needs it: Growth agents prioritizing user acquisition spend. Token distribution systems that reward high-quality users. DAO governance systems weighting voting power by wallet quality. Lending protocols adjusting credit limits by wallet sophistication. Partnership evaluation agents assessing counterparty quality.

Real-world integration example: “We’re distributing governance tokens to 50,000 early users. Rank each wallet by quality and create a weighted distribution that gives 5x allocation to top-tier users and 0.1x to suspected farmers.”

5. token-ranker

GitHub: chainaware-token-ranker.md

What it does: Assesses the quality of a token’s holder base using ChainAware’s behavioral intelligence. Instead of measuring price or market cap, Token Rank measures who holds the token — the average Wallet Rank of holders, distribution concentration, holder experience levels, and ratio of genuine long-term holders vs farmers and bots. Full explanation: What Is Token Rank?

Who needs it: Investment research agents evaluating token fundamentals beyond price. Listing committees assessing project quality for exchange or launchpad inclusion. Institutional fund managers conducting due diligence. DeFi aggregators ranking protocols by ecosystem health. Portfolio management agents rebalancing based on community quality signals.

Real-world integration example: “Compare the holder quality of these three DeFi tokens before we allocate our $2M fund position. Token A: 0xa1b2…, Token B: 0xc3d4…, Token C: 0xe5f6…”

6. reputation-scorer

GitHub: chainaware-reputation-scorer.md

What it does: Builds a holistic on-chain reputation profile for a wallet — synthesizing transaction history quality, protocol interaction integrity, community participation, governance behavior, and behavioral consistency over time. Unlike trust score (which focuses on fraud risk) or wallet rank (which measures overall quality), reputation score captures community standing: is this wallet a constructive ecosystem participant, a passive holder, or a known bad actor?

Who needs it: DAO governance agents evaluating voting eligibility and weight. Marketplace platforms assessing seller trustworthiness. Peer-to-peer lending agents evaluating borrower reliability without credit bureaus. Grant distribution systems prioritizing applicants by on-chain track record. Community management agents identifying ambassadors and potential governance participants.

Real-world integration example: “We have 200 grant applicants. Score each applicant wallet by on-chain reputation and create a ranked shortlist of the top 20 candidates with the strongest community track record.”

7. trust-scorer

GitHub: chainaware-trust-scorer.md

What it does: Returns a focused trust probability score (0–100%) representing the likelihood that a wallet will behave legitimately in future transactions. Trust score is forward-looking (predicts future behavior) whereas fraud detection is risk-weighted (assesses current risk level). Trust score is useful for tiered access decisions: high trust → full access, medium trust → enhanced monitoring, low trust → additional verification required.

Who needs it: Access control agents managing feature gating in DeFi platforms. KYC-lite systems that use behavioral trust as a supplement to identity verification. Credit scoring agents in decentralized lending. Risk management systems setting leverage limits based on behavioral trust. Customer success agents prioritizing support resources toward trusted users.

Real-world integration example: “User 0x8c2a…e1b3 wants to access our 20x leveraged trading feature. What’s their trust score and should we grant access, require additional verification, or deny?”

8. analyst

GitHub: chainaware-analyst.md

What it does: A general-purpose blockchain intelligence agent that synthesizes multiple ChainAware data points into comprehensive analytical reports. Instead of returning raw scores, the analyst interprets and contextualizes behavioral data — writing narrative summaries, identifying patterns, comparing against benchmarks, and highlighting actionable insights. It’s the layer that converts ChainAware’s data into human-readable intelligence for non-technical stakeholders.

Who needs it: Research report generation pipelines delivering insights to investors or executives. Compliance reporting agents generating regulatory documentation. Due diligence automation tools that need readable summaries, not just numbers. Portfolio review systems briefing fund managers on on-chain developments. Customer intelligence platforms summarizing user behavior for product teams.

Real-world integration example: “Prepare a 2-page due diligence report on wallet 0xf3a1…c7e2 for our investment committee. Cover activity history, risk profile, network connections, and an overall recommendation.”

9. token-analyzer

GitHub: chainaware-token-analyzer.md

What it does: Deep-dives into a specific token — analyzing its smart contract interactions, holder distribution, whale concentration, trading pattern quality (genuine vs wash trading), liquidity depth and health, and on-chain growth metrics. Goes beyond surface-level market cap and volume to assess whether a token has genuine ecosystem traction or manufactured metrics.

Who needs it: Automated trading agents making allocation decisions based on token fundamentals. Listing decision agents at exchanges or launchpads. DeFi yield optimization agents comparing protocol quality before depositing liquidity. Media and research platforms that need data-driven token assessments. Risk management systems setting position limits based on token quality.

Real-world integration example: “Analyze token 0x2c9b…d5f8. Is the trading volume genuine or wash-traded? What does the holder distribution look like? Is this a good candidate for our liquidity mining program?”

10. whale-detector

GitHub: chainaware-whale-detector.md

What it does: Identifies, profiles, and monitors high-value wallet addresses (“whales”) — wallets with significant portfolio value and market influence. Returns whale classification, portfolio composition, recent large movement signals, historical behavior during market events, and behavioral predictions for likely near-term actions. Critical for protocols that derive disproportionate value (and risk) from a small number of large holders.

Who needs it: Protocol treasury management agents monitoring large holder activity. Trading agents that use whale movement signals for position sizing. Marketing and BD agents that prioritize high-value outreach. Liquidity management systems that anticipate large withdrawal events. Investor relations agents tracking institutional wallet behavior. Risk management systems that stress-test against whale exit scenarios.

Real-world integration example: “Alert me if any whales holding more than $5M of our protocol token show signs of preparing to exit. Check the top 50 holders and flag anyone with unusual activity in the last 48 hours.”

11. wallet-marketer

GitHub: chainaware-wallet-marketer.md

What it does: Generates personalized marketing and engagement strategies for a specific wallet based on its behavioral profile. Analyzes experience level, risk tolerance, protocol preferences, and predicted intentions to recommend: the right messaging tone, which product features to highlight, optimal communication timing, appropriate incentive structures, and predicted conversion probability for specific campaigns. Transforms generic marketing into wallet-specific personalization at scale.

Who needs it: Growth automation agents running personalized re-engagement campaigns. CRM systems that need to segment and message crypto users without PII. Airdrop optimization agents targeting the right users with the right messaging. Partnership marketing agents personalizing outreach based on partner community behavioral profiles. Product-led growth systems that dynamically adjust in-app messaging per user segment.

Real-world integration example: “We have 10,000 wallets that connected to our Dapp but didn’t complete onboarding. Analyze each wallet and generate personalized re-engagement messages tailored to their experience level and primary interests.”

12. onboarding-router

GitHub: chainaware-onboarding-router.md

What it does: Instantly classifies a newly connecting wallet and routes it to the appropriate onboarding experience based on behavioral profile. Determines experience level (1–5), risk tolerance, primary activity focus (DeFi, NFT, gaming, trading), and predicted product fit — then recommends the specific onboarding path, feature exposure sequence, support level, and educational content appropriate for that wallet. Turns one-size-fits-all onboarding into dynamic, personalized flows.

Who needs it: Any Dapp or platform with multiple user types that need different first experiences. Financial products that need to match users to appropriate risk-level features from session one. Compliance systems that route high-risk wallets to enhanced verification before full access. Educational platforms that adapt curriculum difficulty to user sophistication. Marketplace onboarding flows that customize the experience for buyers vs sellers vs power traders.

Real-world integration example: “Wallet 0x5d7f…b2c4 just connected for the first time. Analyze their profile and tell me: should we show them the beginner tutorial, the advanced feature tour, or skip onboarding entirely and go straight to the pro dashboard?”

Try Fraud Detector Free

Wallet Auditor — Free

3 Multi-Agent Scenarios

The real power of MCP emerges when multiple agents collaborate — each calling different ChainAware capabilities to accomplish complex tasks that no single agent could handle alone. Here are three production-ready architectures.

Scenario 1: Investment Research Pipeline

A crypto fund’s AI research system needs to evaluate 50 new DeFi protocols per week and deliver investment recommendations to the investment committee. The pipeline involves three coordinating agents:

Agent A — Initial Screening (calls rug-pull-detector + token-ranker): Scans every new protocol automatically. Filters out rug pull risks and low-quality token communities in the first pass. Reduces 50 protocols to 15 worth deeper analysis.

Agent B — Deep Analysis (calls token-analyzer + whale-detector + wallet-ranker): For each surviving protocol, runs full token analysis, identifies whale concentration risk, and assesses the quality of the top 100 holders. Generates quantitative scores for each dimension.

Agent C — Report Generation (calls analyst): Synthesizes all data into investment committee-ready memos with narrative summaries, risk assessments, and buy/watch/pass recommendations.

Total pipeline time: under 2 hours for 50 protocols, compared to 3 days of manual research. Human analysts review the final shortlist of 5–8 high-confidence opportunities.

Scenario 2: Real-Time Compliance Agent

A regulated crypto exchange needs to screen every withdrawal request in real-time without slowing down the user experience. Three compliance agents run in parallel:

Fast Path Agent (calls trust-scorer): Instant trust check runs in <100ms. For high-trust wallets (score 85+), auto-approves withdrawal. Handles 70% of requests without further review.

Standard Review Agent (calls aml-scorer + fraud-detector): For medium-trust wallets (score 50–85), runs full AML and fraud screen. Auto-approves if both pass, escalates if either flags risk.

Enhanced Review Agent (calls analyst + reputation-scorer): For low-trust wallets, generates a full compliance report and reputation assessment that human compliance officers review before decision. All documentation is auto-generated for potential SAR filing.

Result: 70% of withdrawals process instantly, 25% in under 30 seconds, and only 5% require human review — while maintaining full regulatory compliance documentation.

Scenario 3: Growth and Marketing Automation

A DeFi protocol’s growth team uses AI agents to run the entire user acquisition and retention lifecycle without manual segmentation work:

Acquisition Agent (calls wallet-ranker): Scores inbound users from each marketing channel in real-time. Reports Wallet Rank distribution per channel, enabling budget reallocation toward channels that deliver high-quality users (Rank 70+) instead of airdrop farmers (Rank <30). Read more in our Web3 User Segmentation Guide.

Onboarding Agent (calls onboarding-router): Instantly routes each connecting wallet to the right first experience — expert users get the pro dashboard immediately, newcomers get guided tutorials, and high-fraud-risk wallets get additional verification before access. Completion rates increase from 35% to 62%.

Retention Agent (calls wallet-marketer + whale-detector): Monitors all active users for churn signals and whale exit preparation. Automatically triggers personalized retention campaigns for at-risk power users and flags large holder movements to the team before they execute.

Step-by-Step Integration Guide

Getting started with ChainAware MCP takes under 30 minutes for a working integration. Here’s the complete path from zero to production.

Step 1: Get Your MCP API Key

Visit chainaware.ai/mcp and select a subscription plan. All plans provide access to the full MCP server with all 12 agent capabilities. The API key grants authenticated access to ChainAware’s prediction engine for your MCP requests.

Step 2: Clone the GitHub Repository

git clone https://github.com/ChainAware/behavioral-prediction-mcp.git
cd behavioral-prediction-mcp

The repository contains the MCP server configuration and all 12 agent definition files in .claude/agents/. Each .md file is a self-contained agent spec that describes the capability, input format, output structure, and usage examples in a format LLMs natively understand.

Step 3: Configure Your API Key

# Set your ChainAware API key as an environment variable
export CHAINAWARE_API_KEY="your_api_key_here"

# Or add to your .env file
echo "CHAINAWARE_API_KEY=your_api_key_here" >> .env

Step 4: Configure Your MCP Client

If you’re using Claude Desktop or a Claude-compatible environment, add the ChainAware MCP server to your configuration:

{
  "mcpServers": {
    "chainaware": {
      "command": "node",
      "args": ["path/to/behavioral-prediction-mcp/server.js"],
      "env": {
        "CHAINAWARE_API_KEY": "your_api_key_here"
      }
    }
  }
}

For other MCP-compatible frameworks (LangChain, AutoGen, custom LLM pipelines), refer to your framework’s MCP client documentation. The MCP quickstart guide covers setup for all major environments.

Step 5: Select the Agents You Need

Copy the relevant agent definition files from .claude/agents/ to your project. Each file is independent — you don’t need all 12. A compliance-focused deployment might only need aml-scorer, fraud-detector, and trust-scorer. A growth platform might only need wallet-ranker, onboarding-router, and wallet-marketer.

Step 6: Test with Natural Language

Once configured, test your integration by asking your agent natural language questions: “Check if wallet 0x1234…5678 is safe to transact with”, “What’s the fraud risk on this address?”, “Give me the Wallet Rank for 0xabcd…ef01”, “Is this token’s volume genuine or wash-traded?”, “Should we onboard this new user to beginner or expert flow?”

The agent autonomously selects the appropriate ChainAware tool, calls it, and incorporates the result into its response. No code changes needed when you want different behavior — just update your prompt.

Step 7: Deploy to Production

For production deployments, consider:

• Caching: Wallet behavioral profiles don’t change by the second. Cache results for 1–6 hours to reduce API call volume.
• Batching: For bulk operations (ranking 10,000 wallets), use the batch endpoints in the ChainAware API alongside MCP for individual real-time calls.
• Error handling: Implement fallback logic for cases where the MCP server is unavailable. For compliance-critical workflows, fail closed (deny action) rather than fail open.
• Logging: Capture all MCP tool calls and responses for audit trails, especially for compliance and fraud decision workflows.

Use Cases by Domain

ChainAware MCP agents aren’t just for crypto companies. Any AI system that handles financial relationships, identity verification, or community management can benefit from blockchain behavioral intelligence. Here’s how different domains apply the 12 agents.

Financial Services & FinTech

• Payment processors: fraud-detector + aml-scorer for every crypto payment acceptance
• Neo-banks with crypto rails: trust-scorer for tiered feature access without full KYC
• Crypto lending platforms: wallet-ranker + reputation-scorer for creditworthiness assessment
• Insurance underwriters: analyst for crypto custody risk reports

Institutional Investment

• Crypto funds: Full pipeline using rug-pull-detector → token-ranker → token-analyzer → analyst
• Trading desks: whale-detector for large holder movement signals
• Research platforms: token-analyzer for data-driven token assessments
• Portfolio managers: wallet-ranker for portfolio-wide quality scoring

DeFi & Web3 Products

• DEXs and lending protocols: fraud-detector + trust-scorer for real-time transaction screening
• NFT marketplaces: reputation-scorer for seller trust, whale-detector for high-value buyer identification
• DAOs: reputation-scorer + wallet-ranker for governance weight calibration
• Launchpads: rug-pull-detector + token-analyzer for project screening

Compliance & Legal

• Blockchain forensics firms: analyst for court-ready investigation reports
• Regulatory tech platforms: aml-scorer integrated into existing compliance workflows
• Law firms: reputation-scorer + analyst for litigation support
• Audit firms: wallet-ranker + fraud-detector for crypto-holding client assessment

Marketing & Growth

• Web3 marketing platforms: wallet-marketer for personalized campaign generation
• CRM systems: wallet-ranker for behavioral segmentation without PII
• Growth automation tools: onboarding-router for intelligent user flow selection
• Token distribution platforms: wallet-ranker for anti-sybil, quality-weighted distributions

Frequently Asked Questions

Do I need to know blockchain or crypto to use these agents?

No. The entire point of MCP is abstraction — your AI agent understands and calls the tools in natural language. You describe what you want (“check if this wallet is trustworthy”) and ChainAware’s MCP server handles all the blockchain-specific complexity. You need a ChainAware API key and the agent definition files. No crypto expertise required.

Which AI systems are compatible with ChainAware MCP?

Any MCP-compatible system, including Claude (all versions), GPT-4 and later (via MCP bridges), open-source models running in MCP-compatible frameworks, LangChain agents, AutoGen multi-agent systems, and custom LLM pipelines. The agent definition files in the GitHub repo are written in Markdown and are broadly compatible. The specific integration path depends on your LLM framework — see the MCP documentation for framework-specific setup.

What data does ChainAware analyze and how accurate is it?

ChainAware analyzes 14M+ wallet addresses across 8 blockchains (Ethereum, BNB Smart Chain, Polygon, Base, Solana, Avalanche, Arbitrum, Haqq Network). All data is derived from public on-chain transaction history — no personal information is collected or required. Fraud prediction accuracy is 98%, measured as F1 score on held-out test data. Inference latency is <100ms for real-time applications. See our AI-Powered Blockchain Analysis Guide for the technical methodology.

What’s included in each MCP subscription plan?

All subscription plans provide access to the full MCP server with all 12 agent capabilities. Plans differ by monthly API call volume, rate limits, SLA guarantees, and enterprise features (dedicated infrastructure, custom model training, compliance reporting). Visit chainaware.ai/mcp for current pricing and plan details.

Can I use multiple agents in the same workflow?

Yes — and this is where MCP’s value truly shines. Your AI agent can call multiple ChainAware tools in sequence or parallel within a single task. A due diligence workflow might call fraud-detector, then aml-scorer, then reputation-scorer, then ask analyst to synthesize everything into a report — all in one natural language conversation with no code changes.

Is the GitHub repository open source? Can I modify the agents?

Yes. The agent definition files in the behavioral-prediction-mcp GitHub repository are open source. You can fork the repo, modify agent descriptions, adjust behavior, and create custom agent definitions that call ChainAware’s underlying capabilities in new ways. The MCP subscription covers API access; the agent definitions themselves are free to use and modify.

How does MCP compare to ChainAware’s REST API?

The REST API is best for developer-built integrations where you control the code and want deterministic, direct API calls. MCP is best for AI agent integrations where you want autonomous tool selection, natural language invocation, and composability with other MCP-compatible tools. Many production systems use both: REST API for bulk batch processing and high-throughput workloads, MCP for AI agent real-time decision-making. They access the same underlying prediction engine.

What happens if ChainAware doesn’t have data on a wallet?

For wallets not yet in ChainAware’s 14M+ database (very new addresses or low-activity wallets), the agents return available data with confidence intervals and explicitly flag limited data scenarios. The agent definitions include guidance on interpreting low-confidence results — typically, new wallets with no history receive conservative risk assessments (medium risk, limited trust) until behavioral history accumulates.

Conclusion

The emergence of MCP as an open standard for AI agent tool integration marks a fundamental shift in how blockchain intelligence gets deployed. For years, accessing on-chain behavioral data required deep crypto expertise, custom API integration work, and constant maintenance as interfaces evolved. With ChainAware’s 12 pre-built MCP agents, that barrier is gone.

Any AI agent — compliance bot, investment research system, growth automation platform, due diligence pipeline — can now call upon 14 million wallet behavioral profiles, 98% accurate fraud prediction, real-time AML screening, and comprehensive token analysis in natural language. The same way your agent calls a weather API or a CRM database, it can now call blockchain intelligence. No crypto knowledge required.

The 12 agents cover the full spectrum of blockchain intelligence use cases: security (fraud-detector, rug-pull-detector, aml-scorer, trust-scorer), quality assessment (wallet-ranker, token-ranker, reputation-scorer), market intelligence (analyst, token-analyzer, whale-detector), and growth (wallet-marketer, onboarding-router). Together they form a complete toolkit for any AI system that touches financial relationships, identity trust, or community management.

The open-source nature of the agent definitions means the community can extend, remix, and build on top of ChainAware’s capabilities. New use cases will emerge that the ChainAware team hasn’t imagined. That’s the power of building on open standards.

Clone the repo. Get your API key. Give your agent blockchain superpowers.

About ChainAware.ai

ChainAware.ai is the Web3 Predictive Data Layer — the infrastructure layer powering blockchain intelligence for AI agents, DeFi protocols, exchanges, compliance teams, and enterprises. Our ML models analyze 14M+ wallets across 8 blockchains, delivering 98% accurate fraud prediction, behavioral segmentation, AML screening, and comprehensive wallet intelligence via API and MCP. Backed by Google Cloud, AWS, and leading Web3 VCs.

Learn more at ChainAware.ai | MCP Integration: chainaware.ai/mcp | GitHub: behavioral-prediction-mcp

Clone GitHub Repo

Get MCP API Key

Try Fraud Detector Free

Request Enterprise Demo

The post 12 Blockchain Capabilities Any AI Agent Can Use (MCP Integration Guide) first appeared on ChainAware.ai.

Crypto theft hit a new record in 2025. According to Chainalysis’s 2025 Crypto Crime Report, illicit activity involving crypto wallets — spanning phishing, rug pulls, smart contract exploits, private key theft, and social engineering — accounted for tens of billions in losses from individual users and protocols alike. The attack surface is expanding. The sophistication of threats is growing. And the defenses most crypto users rely on are falling behind.

The conventional security advice — use a hardware wallet, never share your seed phrase, check contract addresses carefully — remains valid. But it is no longer sufficient. These measures protect against threats you can see coming. They do nothing to protect you from the threats you cannot see: the counterparty whose wallet looks legitimate but whose behavioral history contains every pattern associated with fraud preparation; the liquidity pool whose contract passes a surface audit but whose creator wallet has already run two previous rug pulls.

Behavioral intelligence is the security layer that closes these gaps. Rather than checking whether a counterparty’s funds are clean, behavioral AI predicts whether that counterparty is likely to commit fraud based on their on-chain behavioral history — with 98% accuracy, in real time, before you send a single satoshi.

This guide covers the full 2026 threat landscape: what each major attack vector looks like, how it has evolved, where traditional defenses succeed and where they fail, and how behavioral intelligence addresses the gaps that conventional security cannot close.

The 2026 Crypto Threat Landscape: Scale and Evolution

Three structural factors make crypto uniquely vulnerable. First, irreversibility: blockchain transactions cannot be reversed. Second, pseudonymity: most addresses are not linked to verified identities — the only record is on-chain behavioral history. Third, complexity and speed: DeFi moves faster than most users can evaluate safely. According to the US Federal Trade Commission, urgency is the most consistently reported feature of successful crypto scams.

Threat 1: Phishing, Wallet Drainers & Approval Attacks

Classic phishing uses homograph attacks — lookalike Unicode URLs invisible to the naked eye. Approval phishing tricks users into signing unlimited spending permissions. According to Elliptic’s DeFi risk research, approval phishing now accounts for the majority of high-value individual crypto theft. Airdrop drain attacks send worthless tokens whose interaction triggers drain contracts.

Threat 2: Rug Pulls and Exit Scams

Variants: hard rug (instant total drain), soft rug (gradual team sell-off), slow abandonment, and honeypot contracts (buy but cannot sell). The most dangerous misconception is that a smart contract audit makes a protocol safe — audits check code, not intentions. The ChainAware Rug Pull Detector checks the behavioral history of creator wallets, not source code.

Threat 3: Smart Contract Exploits

Major categories: reentrancy attacks, oracle manipulation, access control flaws, and cross-chain bridge exploits (Ronin $625M, Wormhole $320M). See our AI-Powered Blockchain Analysis guide.

Threat 4: Private Key and Seed Phrase Theft

The four paths: malware/info-stealers (RedLine, Raccoon, Vidar), clipboard hijacking, seed phrase phishing (fake recovery sites), and supply chain attacks. See our Predictive AI for Crypto KYC & AML guide.

• Hardware wallet (Ledger, Trezor, Coldcard) for any significant holdings
• Seed phrase offline only — paper or metal, never digital or photographed
• Dedicated device for crypto transactions
• Transaction simulation to preview what each transaction does before signing
• Never enter a seed phrase anywhere except your hardware wallet’s physical interface
• Audit active token approvals regularly using Revoke.cash
• Multi-signature wallets for organizational or high-value holdings

Threat 5: Social Engineering and Impersonation

Vectors: pig butchering (FBI reports this as the largest single category of crypto fraud losses), fake team impersonation, support scam DMs, and undisclosed KOL paid promotion. As documented in our influencer marketing in crypto analysis, on-chain behavioral history is the most reliable legitimacy signal.

“Social engineering exploits the one vulnerability that hardware wallets and audits cannot address: human judgment under manufactured urgency and misplaced trust. The defense is systematic counterparty verification — not faster decision-making.”

Traditional Defenses: What They Cover and Where They Fail

The critical gap is counterparty behavioral risk — every traditional measure protects your own wallet but tells you nothing about the other party. See our Transaction Monitoring vs AML guide.

The Behavioral Intelligence Layer

Behavioral intelligence is built on a foundational insight: on-chain behavioral history is the most reliable predictor of future fraudulent behavior. Fraud patterns — mixing protocol usage, sybil cluster coordination, anomalous transaction timing — are detectable by AI models trained on millions of confirmed fraud cases across 8 blockchains. Fraud is frequently committed with clean funds — professional operators fund attack wallets through legitimate channels to pass AML checks. Behavioral patterns reveal intent where fund origin cannot. See our Forensic vs AI-Powered Blockchain Analysis guide.

Fraud Detector: Check Unknown Addresses Before Transacting

The ChainAware Predictive Fraud Detector evaluates any wallet address across seven behavioral dimensions: transaction patterns, counterparty network mapping, protocol interaction history, mixing protocol detection, sybil cluster analysis, fund movement patterns, and AML status. Output is a Trust Score — 95%+ is clean, below 50% warrants caution, below 30% is a strong warning. Use before sending funds to any new counterparty, interacting with a new contract deployer, or joining any new protocol. See the Fraud Detector complete guide.

Rug Pull Detector: Screen Unknown Pools and Contracts

The ChainAware Predictive Rug Pull Detector checks the behavioral history of the humans behind a contract — creator wallet history, LP provider profiles, token distribution patterns, and cross-protocol behavioral signatures. 68% accuracy catches rug pull risk that code audits entirely miss. Use when: launched within 90 days, APY above 50%, anonymous team, heavy KOL promotion, or no reputable audit. See the Rug Pull Detector complete guide.

The Complete 2026 Wallet Security Workflow

Layer 1: Key and Device Security

• Hardware wallet for all significant holdings
• Seed phrase offline only — never photographed, never in cloud storage
• Dedicated device for crypto transactions where possible
• Active token approval management — audit and revoke unused approvals monthly
• Multi-signature wallet for organizational funds or holdings above $50,000

Layer 2: Transaction Verification Before Signing

• Verify site URLs character-by-character before connecting wallet
• Use transaction simulation to preview exactly what each transaction will do
• Never sign setApprovalForAll without independently verifying the requesting protocol
• Urgency is a social engineering signal — always pause for high-value transactions

Layer 3: Counterparty Behavioral Intelligence

• Run the Fraud Detector on any address you’re sending significant funds to for the first time
• Run the Rug Pull Detector on any pool or contract you haven’t previously vetted
• Check the Wallet Auditor profile of significant counterparties — KOLs, advisors, partners
• Consider the Transaction Monitoring Agent for ongoing protocol relationships

Layer 4: Social Engineering Defense

• Verify all urgent communications through official channels before acting
• No legitimate team will contact you unsolicited via DM with opportunities or alerts
• KOL endorsements are not security validation — check on-chain profiles independently
• If an opportunity requires immediate action, that urgency is itself a red flag

For Platforms: Protecting Users at the Protocol Level

The Transaction Monitoring Agent deploys via Google Tag Manager and continuously screens every connecting wallet 24×7. When a wallet’s Trust Score drops significantly, your team receives an immediate Telegram alert. The Credit Scoring Agent monitors borrower creditworthiness continuously for lending protocols. See the ChainAware complete product guide.

Frequently Asked Questions

The post Crypto Wallet Security 2026: Behavioral Intelligence & Fraud Prevention first appeared on ChainAware.ai.