Estimated Time: 30 minutes
Difficulty Level: ⭐⭐ Beginner
Difficulty Level: ⭐⭐ Beginner
Objective
Build an AI assistant with on-chain awareness: Capabilities:- ✅ Query Token prices and balances
- ✅ Analyze wallet holdings
- ✅ Track Smart Money
Step 1: Configure MCP
Prerequisites
- ChainStream account (to get Client ID and Client Secret)
- Claude Desktop or Cursor
- Node.js 18+
Install MCP Server
Configure Claude Desktop
Edit the configuration file:- macOS
- Windows
For detailed steps, refer to the MCP Setup Guide.
Step 2: Conversation Examples
Example 1: Check ETH Price
Example 2: Analyze Wallet Holdings
Example 3: Track Smart Money
Step 3: Advanced Usage
Multi-step Analysis
Comparative Analysis
Security Considerations
Strategy Limitations
The AI assistant only provides data queries and analysis, not direct trade execution.Human Confirmation
For important decisions, AI provides analysis but recommends human confirmation:Extension: Custom Agent
Build with MCP SDK
Available MCP Tools
FAQ
Claude not calling MCP tools?
Claude not calling MCP tools?
- Confirm MCP Server is configured correctly
- Restart Claude Desktop
- Check if Client ID and Client Secret are valid
- Try more explicit prompts like “Use ChainStream to query…”
Response too slow?
Response too slow?
On-chain data queries take time, especially for complex analysis. You can:
- Ask step by step to reduce single query load
- Specify a specific chain to reduce query scope
Can AI auto-trade?
Can AI auto-trade?
The current version only supports data queries, not direct trade execution. This is for security reasons. For automated trading, we recommend executing through a separate trading system based on AI analysis results.
Related Documentation
MCP Setup Guide
Detailed configuration steps
MCP Tools Catalog
View all available tools

