OpenRuna
Sign in
← Workflows

Build your first AI MCP Server

32 nodes · agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow

Engine
n8n
Nodes
32
Trigger
scheduled/triggered
Source file
1184_Debughelper_HTTP_Create_Webhook.json

Workflow flow

IntegrationsAgentGoogleCalendarToolMCPExecuteWorkflowSwitchToolWorkflowChatMemoryBufferWindowMcpClientToolDebugHelperHTTPLmChatOpenAi+8 more
100%

SearchEvent

GoogleCalendarTool

CreateEvent

GoogleCalendarTool

UpdateEvent

GoogleCalendarTool

DeleteEvent

GoogleCalendarTool

TRIGGER

Google Calendar MCP

@n8n/n8n-nodes-langchain.mcp

TRIGGER

When Executed by Another Workflow

ExecuteWorkflow

Convert Text

@n8n/n8n-nodes-langchain.toolWorkflow

TRIGGER

When chat message received

@n8n/n8n-nodes-langchain.chat

Simple Memory

@n8n/n8n-nodes-langchain.memoryBufferWindow

Calendar MCP

@n8n/n8n-nodes-langchain.mcpClientTool

My Functions

@n8n/n8n-nodes-langchain.mcpClientTool

TRIGGER

My Functions Server

@n8n/n8n-nodes-langchain.mcp

Generate random user data

@n8n/n8n-nodes-langchain.toolWorkflow

Random Jokes

@n8n/n8n-nodes-langchain.toolWorkflow

OpenAI 4o

@n8n/n8n-nodes-langchain.lmChatOpenAi

AI Agent

@n8n/n8n-nodes-langchain.agent

Switch

Switch

Convert Text to Upper Case

Set

Convert Text to Lower Case

Set

Random user data

DebugHelper

Joke Request

HTTP

Return only some fields

Set

22 steps · flows top to bottom, branches left to right

Browse by integration

Browse all integrations →

Import into n8n

  1. Download the n8n JSON file (full or sanitized).
  2. In n8n: Workflows → Import from file.
  3. Open each node and reconnect credentials to your accounts.
  4. Test with manual execution before enabling triggers.

Sanitized JSON removes credential IDs — safer for sharing. Flow graph JSON is OpenRuna's lightweight format for diagrams and other tools, not n8n import.

View source corpus ↗

Overview

Build your first AI MCP Server (32-node n8n automation, agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow) is free on OpenRuna — view the graph and export the JSON to import into n8n.

What this workflow does

"Build your first AI MCP Server" is an n8n automation built from 32 nodes spanning agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow. 32 nodes · agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow A scheduled/triggered entry point kicks it off, and each node passes data to the next until the run completes. On OpenRuna you get the visual graph, the integration list, and a downloadable JSON ready to import into n8n. Use it to learn integration patterns, fork it for your own use case, or deploy it quickly after reconnecting credentials.

Use cases

  • Benchmark it against your current agent integration to spot missing steps or redundant nodes.
  • Fork it to add error handling, retries, or a notification step without designing the 32-node flow from scratch.
  • Use it as a starting template when wiring agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow — adjust node parameters to your accounts and record IDs.
  • Import "Build your first AI MCP Server" into n8n, reconnect credentials for agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow, and run the same automation in your own workspace.

Example output

Imported into n8n, "Build your first AI MCP Server" exposes 32 configured nodes. Trigger type: scheduled/triggered. Integrations: agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow. Reconnect the agent credential first, then walk the remaining nodes top to bottom. Run it once in test mode to verify any branch logic (Switch/IF nodes) before enabling production triggers.

Tips by platform

Claude

Paste the exported JSON for "Build your first AI MCP Server" into Claude and ask it to explain each of the 32 nodes. Claude is good at suggesting credential mappings for agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow, plus error-handling and idempotency improvements before you run it in production.

ChatGPT

Have ChatGPT generate a checklist for adapting "Build your first AI MCP Server" to your accounts — which agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow credentials to create and which node parameters to change first.

Cursor

Open the downloaded JSON in Cursor and use Agent mode to refactor hard-coded URLs into env vars, or to generate tests for any Code nodes. Keep the OpenRuna flow diagram open so you do not break connection order across the 32 nodes.

Frequently asked questions

How do I import "Build your first AI MCP Server" into n8n?
Click Download n8n JSON on this page, then in n8n choose Workflows → Import from file and select the downloaded file. Reconnect credentials on each node — the export carries credential IDs from the original author's instance, not working secrets.
Which integrations does "Build your first AI MCP Server" use?
It uses: agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow. The flow diagram above shows how each service connects across the 32 nodes. Filter OpenRuna by integration to find related workflows and tools.
Can I import a sanitized export without credentials?
Yes. Use "Download sanitized JSON" to strip credential references before sharing internally. You will still add your own agent and googleCalendarTool credentials in n8n after import.
What trigger type does "Build your first AI MCP Server" use?
Trigger type: scheduled/triggered. After import, confirm the trigger node (webhook, schedule, or app event) matches your environment, then activate the workflow when you are ready to run it.
Is "Build your first AI MCP Server" free to use?
OpenRuna catalogs community n8n workflows under open licenses. Check the source corpus link for the original license; commercial use may require verifying the third-party API terms for agent, googleCalendarTool, mcp, executeWorkflow, switch, toolWorkflow, chat, memoryBufferWindow.

Related resources