Build with CoreRounder MCP
Connect your AI tools to real-time crypto market data, portfolio analytics, and risk intelligence through the Model Context Protocol.
Model Context Protocol
MCP is an open standard that lets AI assistants like Claude access external data and tools. CoreRounder's MCP server gives your AI direct access to:
- Real-time crypto prices & market data (CoinGecko)
- Technical indicators — RSI, SMA, MACD
- On-chain data — exchange netflow, whale activity
- RAG-powered knowledge search (whitepapers, reports)
- AI investment signal generation
5 MCP Tools
get_crypto_price
Fetch real-time price, 24h change, market cap, and volume for any cryptocurrency.
get_technical_indicators
Calculate RSI, SMA (7/14/30), MACD and generate trend signals.
get_onchain_data
Exchange netflow, active addresses, transaction volume, whale activity.
search_knowledge
RAG-based semantic search across crypto whitepapers, research reports, and news.
generate_ai_signal
Comprehensive AI investment signal combining price, technicals, on-chain, and sentiment.
Get started in 5 minutes
Install dependencies
cd mcp && npm installConfigure environment
cp .env.example .env
# Add your OpenAI API key to .env
OPENAI_API_KEY=sk-your-key-hereBuild the server
npm run buildTest with MCP Inspector
npm run inspectorConnect to Claude Desktop
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"corerounder": {
"command": "node",
"args": ["/path/to/corerounder/mcp/build/index.js"],
"env": {
"OPENAI_API_KEY": "sk-your-key-here"
}
}
}
}Restart Claude Desktop and try: