Query Sage X3 sales, stock, and revenue with OpenRouter Claude and MCP
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 19 nodes and runs when a chat message arrives (plus 1 other trigger). Along the way it connects OpenRouter Chat Model and Nx3 (community).
How it runs
Trigger: When a chat message arrives (plus 1 other trigger).
- Analyse the question and query Sage X (AI Agent): runs an AI agent, with model: Language model (OpenRouter); 14 tools (x3_item_detail, x3_item_search, x3_stock_detail, x3_revenue_billed…); memory: Conversation memory
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-nx3 is verified or supports 3.0 (used in x3_customer_search, x3_item_search, x3_customer_product).
Nodes used (6)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - MCP Server Trigger
@n8n/n8n-nodes-langchain.mcpTrigger - Nx3Soap Tool
n8n-nodes-nx3.nx3SoapTool
From the author
Quick overview This workflow lets users ask natural-language sales, stock, and revenue questions about Sage X3, using an OpenRouter-hosted Claude model to select from predefined Sage X3 SQL tools, and optionally exposing the same tools through a…