Borrowing it
Nothing to install: this file belongs to ChainAware/behavioral-prediction-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ChainAware/behavioral-prediction-mcp/main/CLAUDE.mdgit 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/instructions/chainaware/behavioral-prediction-mcp/claude-md)<a href="https://agentmods.dev/instructions/chainaware/behavioral-prediction-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chainaware/behavioral-prediction-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.04934 | $0.04934 |
| Opus 5 | $0.02467 | $0.02467 |
| Sonnet 5 | $0.00987 | $0.00987 |
| Haiku 4.5 | $0.00493 | $0.00493 |
Grade A, and why
behavioral-prediction-mcp CLAUDE.md 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 6d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Behavioral Prediction MCP
Project Overview
This repository contains the ChainAware Behavioral Prediction MCP — an AI-native Web3 intelligence layer that gives AI agents predictive capabilities over blockchain wallets and smart contracts.
- MCP Endpoint:
https://prediction.mcp.chainaware.ai/sse - API Key: Set as
CHAINAWARE_API_KEYenvironment variable (never hardcode) · x402 payment also supported - GitHub:
https://github.com/ChainAware/behavioral-prediction-mcp - Coverage: 14M+ wallets, 8 blockchains, 1.3B+ data points
- Website: https://chainaware.ai
- 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
- Rug Pull Detection Accuracy: 90.1% backtesting verified
- Featured in: CB Insights Fraud Prevention Market Map for the AI Era (2026)
- Listed on: BNB Chain AI Landscape (2025)
- Listed on: BNB Chain Kickstart — Marketing Tools (2025)
- Awarded: Google Cloud $250k Grant (2025)
- Selected for: AWS Fintech Accelerator (2024)
- Listed on: Safary Club Web3 Growth Landscape — Growth Tools (2024)
MCP Tools (14 total)
| Tool | Purpose | Networks |
|---|---|---|
predictive_fraud |
Fraud probability + AML forensics for a wallet | ETH, BNB, POLYGON, TON, BASE, TRON, HAQQ |
predictive_fraud_batch |
Schedule batch fraud detection for a list of wallets; returns job_id + signature | ETH, BNB, POLYGON, TON, BASE, TRON, HAQQ |
predictive_behaviour |
Wallet segmentation, intent, experience, recommendations | ETH, BNB, BASE, HAQQ, SOLANA |
predictive_behaviour_batch |
Schedule batch behavioural analysis for a list of wallets; returns job_id + signature | ETH, BNB, BASE, HAQQ, SOLANA |
check_job_status |
Poll progress of a batch job (completed / failed / pending counts) | — |
get_job_results |
Retrieve full per-wallet results from a completed or partial batch job | — |
predictive_rug_pull |
Smart contract rug pull risk scoring | ETH, BNB, BASE, HAQQ |
credit_score |
Crypto credit/trust score (1–9) combining fraud + social graph analysis | ETH |
token_rank_list |
Ranked list of tokens by holder community strength | ETH, BNB, BASE, SOLANA |
token_rank_single |
Token rank + top holders for a specific contract | ETH, BNB, BASE, SOLANA |
run_token_audit |
Deep multi-module token contract audit (get-or-create; returns full report if cached or queues job) | eth, bsc, base, arbitrum, avalanche, optimism, polygon |
get_token_audit_result |
Poll/retrieve completed token audit — 8 modules, 0–100 risk score, honeypot analysis | eth, bsc, base, arbitrum, avalanche, optimism, polygon |
agents_trust_score_list |
Paginated list of ERC-8004 registered AI agents with trust scores 0–1000 | — |
agents_trust_score_single |
Deep trust profile for a single ERC-8004 agent by agent_id + chain_id | — |
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.
- 6d ago First seen · 195 lines · 4,934 tokens per session scan A 058b4c07f2db
behavioral-prediction-mcp CLAUDE.md is an instructions file published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 26d ago), licensed MIT. It adds 4,934 tokens to every session, about $0.0247 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.