N8n MCP Server + MCP Client: a Hacker News research agent with the tools in their own workflow

n8n MCP Server and MCP Client in two separate workflows: a small research agent I built to keep the AI’s reasoning apart from the tools it calls.

Workflow 1: MCP_Server

Workflow 2: MCP_Client

  • When chat message received → AI Agent
  • Chat model: Google Gemini
  • Tool: MCP Client, pointed at the server’s URL

Why split it
The agent only decides what it needs. The server decides how each tool actually runs. So:

  • a new tool is one more node on the MCP Server Trigger, and the agent workflow doesn’t change
  • Gemini can be swapped for Claude or GPT in the client without touching the tools

Tips if you build one

  • The MCP Client needs the server’s Production URL, and the server workflow must be active for that URL to answer. The Test URL only works while the editor is listening.
  • Give each tool a clear description. It’s what the agent reads when it decides which tool to call.
  • Turn on authentication in the MCP Server Trigger before the server is used outside testing.

What would you put behind an MCP server first?

Something read-only, like your HN tool but pointed at your own data. For example a search on your tickets or CRM that can only get records and never update them.

Your split helps here too, I guess. If the agent only decides what and the server decides how, the server is also where you decide what each caller can touch, and that stays the same when you swap Gemini for Claude. The auth on the MCP Server Trigger is where that starts. I wouldn’t put a write tool behind it until you know who is calling and can limit what that caller sees.

One thing I’d test with this separation is how the agent handles tool failures.

For example, an empty Hacker News result, an API timeout, and a rate-limit error shouldn’t all look like an empty list to the client

I’d give each tool a consistent response structure with a status, source, retrieval timestamp, and an explicit error state where needed

That way, the agent can distinguish “nothing found” from “couldn’t retrieve the data” instead of producing a confident answer from an incomplete result.

The model may change, but that reliability contract can stay the same.

Great test list, thanks. I haven’t tried those three cases on this one yet, and you’re right that “nothing found” and “couldn’t fetch” need to look different to the agent.

What I’d try: wrap the Hacker News node in a sub-workflow (Call n8n Workflow Tool) that always returns the same shape: status, source, retrieved_at, items, and an error message when it fails. With the node’s On Error set to “Continue (using error output)”, a timeout or rate limit comes back as status “error” instead of an empty list. Then the tool description tells the agent to say it couldn’t get the data rather than answer from nothing.

Good point. The Hacker News tool is read-only already (it only has Get many items), and pointing the same setup at your own tickets or CRM is a natural next step. The split helps there too, like you said: the server decides what each tool can touch, so swapping the model doesn’t change who can see what.

Agreed on auth first. I’d keep write tools out until I know who’s calling and what they should see.