PostgreSQL conversational agent with Claude & DeepSeek (Multi-KPI, Secure)
π§ Conversational PostgreSQL Agent Enable AI-driven conversations with your PostgreSQL database using a secure and visual-free agent powered by n8nβs Model Context Protocol (MCP). This template allows users to ask mul...
Template notes
π§ Conversational PostgreSQL Agent
Enable AI-driven conversations with your PostgreSQL database using a secure and visual-free agent powered by n8nβs Model Context Protocol (MCP). This template allows users to ask multiple KPIs in a single message, returning consolidated insights β more efficient than the original Conversing with Data template.
---
π Why This Template
Unlike the Conversing with Data workflow, which handles one KPI per message, this version:
- β Supports multi-KPI questions - β Returns structured, human-readable reports - β Uses fewer AI calls, making it faster and cheaper - β Avoids raw SQL execution for enhanced security
π² Estimated cost per full multi-request run: ~$0.01
This template is optimized for efficiency. Each message can return 2β4 KPIs (You can change the MaxIteration of the Agent to make it more, it is currently set up at 30 iterations) using a single Claude 3.5 Haiku session and DeepSeek-based SQL generation β balancing speed, reasoning, and affordability.