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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.