n8n templateFreeBy Thomas Janssen

AI Assistant which answers questions with a RAG MCP and a Search Engine MCP

Build an AI Agent which accesses two MCP Servers: a RAG MCP Server and a Search Engine API MCP Server. This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Tutorial ![th...

AILangchainCore NodesChat TriggerAgentLm Chat Open AiMemory Buffer Window

Loading interactive preview...

Template notes

Build an AI Agent which accesses two MCP Servers: a RAG MCP Server and a Search Engine API MCP Server.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Tutorial ![thumbnail.png](fileId:1877) [Click here to watch the full tutorial on YouTube!](https://youtu.be/GB2RZ25HTD8)

How it works We build an AI Agent which has access to two MCP servers: - An MCP Server with a RAG database ([click here for the RAG MCP Server](https://n8n.partnerlinks.io/5403-build-an-mcp-server-which-answers-questions-with-retrieval-augmented-generation) - An MCP Server which can access a Search Engine, so the AI Agent also has access to data about more current events

Installation 1. In order to use the MCP Client, you also have to use [MCP Server Template](https://n8n.partnerlinks.io/5403-build-an-mcp-server-which-answers-questions-with-retrieval-augmented-generation).

2. Open the MCP Client "MCP Client: RAG" node and update the SSE Endpoint to the MCP Server workflow

3. Install the "n8n-nodes-mcp" community node via settings > community nodes ![InstalltheMCPCommunityNodewithnpm.png](fileId:1598)

4. ONLY FOR SELF-HOSTING: In Docker, click on your n8n container. Navigate to "Exec" and execute the below command to allow community nodes: