How to add a vector store retriever module between "chat message received" and "AI agent"?

Describe the problem/error/question

Hi, I'm looking for some assistance with a problem.
How can I insert a vector store retriever module between the “chat message received” trigger and the “AI agent” node?

When constructing an AI Agent flow, I need to call some MCP services. Prior to that, I need to perform some information augmentation, similar to RAG (specifically, adding it to the context, not based on LLM output).

Is there a method to integrate the Vector Store Retriever before the AI Agent? Alternatively, is there a way to prevent the LLM module from generating output? Thank you for your guidance.

微信截图_20250521145111523×554 119 KB

Information on your n8n setup

• n8n version:1.93.0
• Running n8n via (Docker, npm, n8n cloud, desktop app):docker