chainlink-sentinel
MCP server for Chainlink ecosystem monitoring with 6 tools: price feed tracking, VRF monitoring, automation status, CCIP tracking, and staking analytics. MIT licensed.
README
Chainlink Sentinel
AI-powered cross-chain risk monitor using Chainlink Data Feeds. Reads on-chain oracle data across 6 EVM chains, detects anomalies in real-time, and generates actionable risk intelligence — all as MCP tools for AI agents.
What it does
- Cross-chain oracle scanning: Reads 30+ Chainlink price feeds across Ethereum, Polygon, Arbitrum, Base, Avalanche, and BNB Chain
- Anomaly detection: Identifies stale oracles, stablecoin depegs, cross-chain price deviations, and potential oracle attacks
- Risk reports: Generates comprehensive risk assessments with severity scoring, chain health metrics, and recommendations
- Zero config: No API keys needed. Uses Chainlink's on-chain data via public RPCs
Built with Chainlink
| Chainlink Product | Usage |
|---|---|
| Data Feeds | Primary data source — reads AggregatorV3Interface across all chains |
| CRE | Cross-chain runtime for multi-chain oracle monitoring |
| CCIP | Cross-chain message passing for alert propagation (planned) |
MCP Tools (6)
| Tool | Description |
|---|---|
sentinel_scan |
Full cross-chain scan — all feeds, all chains, all anomalies |
sentinel_chain |
Scan a specific chain (ethereum, polygon, arbitrum, etc.) |
sentinel_feed |
Read a single Chainlink price feed |
sentinel_stablecoins |
Monitor USDC/USDT/DAI pegs across all chains |
sentinel_risk_report |
Generate AI risk report with recommendations |
sentinel_compare |
Compare a price pair across chains (detect deviations) |
Quick Start
# Install
npm install
# Build
npm run build
# Run as MCP server
npm start
Use with Claude Code
Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"chainlink-sentinel": {
"command": "node",
"args": ["/path/to/chainlink-sentinel/dist/index.js"]
}
}
}
Then ask Claude: "Run a cross-chain sentinel scan" or "Check stablecoin pegs"
Architecture
┌─────────────────────────────────────────────────────┐
│ AI Agent (Claude/Cursor) │
│ via MCP Protocol │
└─────────────────────┬───────────────────────────────┘
│
┌─────────────────────▼───────────────────────────────┐
│ Chainlink Sentinel MCP Server │
│ ┌──────────┐ ┌──────────────┐ ┌────────────────┐ │
│ │ Feed │ │ Anomaly │ │ Risk Analysis │ │
│ │ Reader │ │ Detector │ │ Engine │ │
│ └────┬─────┘ └──────────────┘ └────────────────┘ │
└───────┼─────────────────────────────────────────────┘
│
┌───────▼─────────────────────────────────────────────┐
│ Chainlink Data Feeds (On-Chain) │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌──────────┐ │
│ │Ethereum │ │Polygon │ │Arbitrum │ │Base/Avax │ │
│ │9 feeds │ │5 feeds │ │4 feeds │ │/BNB │ │
│ └─────────┘ └─────────┘ └─────────┘ └──────────┘ │
└─────────────────────────────────────────────────────┘
Anomaly Types
| Type | Severity Logic | Description |
|---|---|---|
| Stale Oracle | >1h major, >2h minor | Oracle hasn't updated within expected heartbeat |
| Depeg | >0.5% warning, >5% critical | Stablecoin deviating from $1.00 peg |
| Cross-chain Deviation | >2% medium, >10% critical | Same pair showing different prices on different chains |
| Flash Crash | Price drop >20% in 1 round | Sudden price movement suggesting manipulation |
Feeds Supported (30+)
BTC/USD, ETH/USD, SOL/USD, LINK/USD, USDC/USD, USDT/USD, DAI/USD, AAVE/USD, UNI/USD, MATIC/USD, ARB/USD, AVAX/USD, BNB/USD — across 6 chains.
Convergence Hackathon
Track: CRE & AI / Risk & Compliance
Why Chainlink Sentinel matters:
- DeFi protocols need real-time oracle health monitoring
- Cross-chain deviations signal arbitrage or attacks
- Stablecoin depeg detection prevents cascading liquidations
- AI agents can autonomously act on risk intelligence
Differentiation:
- First MCP-native Chainlink monitoring tool
- Works with any AI agent (Claude, Cursor, Windsurf)
- Zero API keys — reads directly from on-chain Chainlink contracts
- Cross-chain by default — not single-chain monitoring
License
MIT
Author
Elrom Eved El Elyon — @opencllaw
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。