All Field Notes
RESOURCE CHECKLIST

n8n + MCP setup checklist: server, client, auth, HITL

USE THIS BEFORE YOU SHIP

A copy-paste checklist for wiring the Model Context Protocol into n8n without leaving a hole. Pick a direction (Server Trigger vs Client Tool vs the native server), default the transport to Streamable HTTP, authenticate every server, scope tools to the job, put human-in-the-loop on anything irreversible, and keep PII-touching tools self-hosted. Full walkthrough in the n8n + MCP playbook.

Print it, tick the boxes, ship safely. Each phase maps to a section of the full MCP playbook. US-first compliance notes, then UK/EU, then AU.

Phase 0 Prerequisites

  • ☐ n8n v2.18.4+ if you want the native instance MCP server (Public Preview since April 2026; Cloud, Enterprise, or self-hosted Community).
  • ☐ Decide your transport: Streamable HTTP for anything new. SSE is deprecated, keep it only as a fallback for legacy servers.
  • ☐ A credentials store ready (n8n credentials, not hard-coded tokens).

Phase 1 Pick the direction

  • MCP Server Trigger, you want Claude / Cursor / ChatGPT (or another agent) to call your workflows as tools. n8n is the server.
  • MCP Client Tool, you want an n8n AI Agent to use tools from a system you already run. n8n is the client.
  • Native instance MCP server, you want an assistant to build and deploy workflows inside n8n itself.
  • ☐ One-click managed connection, for Notion, Linear, monday.com, Apify, PostHog you may not need to wire anything by hand.

Phase 2 Build the server / wire the client

  • ☐ Server: add an MCP Server Trigger, set a Path, attach only the tool nodes you intend to expose.
  • ☐ Client: drop an MCP Client Tool on the AI Agent's Tools port, paste the external server URL, set serverTransport = httpStreamable.
  • ☐ Write tool descriptions like you're briefing a new hire, vague descriptions are the #1 reason an agent ignores a tool.

Phase 3 Authenticate (never skip)

  • ☐ Never expose a server with authentication: none.
  • ☐ Use Bearer or header auth; store the token in n8n credentials, never in the URL.
  • ☐ Confirm an unauthenticated request is refused. Rotate the token on your normal secret cadence.

Phase 4 Scope tools to the job

  • ☐ Whitelist only the tools a role needs (include: selected + an explicit includeTools list).
  • ☐ A read-only support agent gets get_order_status, not issue_refund.
  • ☐ Re-check scope whenever the upstream server adds tools.

Phase 5 Human-in-the-loop on anything irreversible

  • ☐ Require explicit human approval (n8n's 2026 tool-level HITL) before any tool that moves money, sends an external message, or deletes data.
  • ☐ Wire the approval prompt to Slack or Telegram ("Approve / Reject").
  • ☐ Test it: inject a sample input each month and confirm it lands in the human queue.

Phase 6 Data residency & logging (US → UK/EU → AU)

  • ☐ Log every tool call (timestamp, tool, redacted input, output, approver) to an append-only store.
  • US: data routed through a third-party MCP server is a disclosure under CCPA/CPRA, prefer no-train vendors with SOC 2, or self-host the tool.
  • EU/UK: sending personal data to a US-hosted server/model is a Chapter V transfer under GDPR/UK GDPR; if MCP tools power a user-facing agent, the EU AI Act Article 50 disclosure duty applies from 2 Aug 2026.
  • AU: APP 8 cross-border disclosure. Keep PII-touching tools on infrastructure you host; redact before any prompt leaves the network.

Want this done for you?

NexFlow wires MCP into your stack with scoped tools, authenticated transport, human-in-the-loop, and an audit log. Custom workflow (cloud, keep your subscriptions), from $750. Local self-hosted setup (removes the monthly subscriptions), from $1,500 one-off.

Sources & method

  1. n8n Docs, MCP Server Trigger and MCP Client Tool.
  2. n8n release notes (2026), native instance MCP server (Community v2.18.4+); tool-level human-in-the-loop. SSE→Streamable HTTP transport.
  3. Full walkthrough: n8n + MCP playbook. Export-ready JSON: workflow snippets.