How to Use the n8n (AI Workflow Automation) MCP in Google ADK

Q: How can I use the Google ADK and n8n (AI Workflow Automation) to build a dashboard in Looker Studio?

Your Gemini agent can use tools like listworkflows and listworkflowexecutions to pull data from n8n. It then writes that data to a BigQuery table, which you connect directly to Looker Studio for visualization.

Q: How do I log n8n (AI Workflow Automation) failures to Google Cloud Logging using the Google ADK?

Create an agent that periodically calls listworkflowexecutions and filters for a 'failed' status. For each failure, it uses getexecutiondetails to get the error log and then writes that structured JSON payload to Cloud Logging.

Q: Does the n8n (AI Workflow Automation) server support filtering for my Google ADK agent?

Yes, listworkflowexecutions accepts parameters to filter runs. This is critical for performance, letting your agent request only failed executions or runs for a specific workflow instead of pulling the entire history.

Q: What n8n credential metadata is exposed to my Google ADK agent, and how is it secured?

The liststoredcredentials tool provides only non-sensitive metadata: the credential's ID, name, type, and timestamps. The actual secrets are never transmitted, and the connection is secured through the Vinkius ephemeral sandbox.

Connect Gemini to your n8n instance using the Google ADK. Audit workflows and pipe execution data directly into BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect n8n (AI Workflow Automation) MCP to Google ADK

Create your Vinkius account to connect n8n (AI Workflow Automation) to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup n8n (AI Workflow Automation) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Centralize n8n Auditing in BigQuery

Stop treating your n8n instance like a black box. Equip your Gemini agent to pull a full inventory of automations with `list_workflows` and `list_workflow_tags`. Now you have a structured list of everything that's deployed. Your agent can then format this data and stream it directly into a BigQuery table. This creates a single source of truth for all your n8n workflows, ready for enterprise-scale analysis and reporting right within your GCP environment.

Monitor Executions at Scale with this MCP Server

Manually checking logs in the n8n UI doesn't scale. Give your agent the `list_workflow_executions` tool to fetch run histories programmatically. You can build a pipeline that monitors for failures across hundreds of workflows automatically. When a failure is detected, the agent uses `get_execution_details` to get the specifics. It can then log that structured error data to Google Cloud Logging or a dedicated BigQuery table for long-term analysis.

Enforce Credential Governance

Your agent can run security audits on your n8n credentials. The `list_stored_credentials` tool provides the metadata needed to check for compliance—things like credential type and age—without ever exposing the secret values. Combine this with `list_instance_users` to cross-reference who has access to what. Your Gemini agent can build a complete map of users, their access rights, and the credentials they've configured, all within your secure GCP project.

Setup guide

Set up n8n (AI Workflow Automation) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with n8n (AI Workflow Automation) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="n8n (AI Workflow Automation)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to n8n (AI Workflow Automation) tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by n8n. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect n8n (AI Workflow Automation) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about n8n (AI Workflow Automation) MCP in Google ADK

Your Gemini agent can use tools like `list_workflows` and `list_workflow_executions` to pull data from n8n. It then writes that data to a BigQuery table, which you connect directly to Looker Studio for visualization.

No, this MCP server is strictly read-only. Your agent can list and get details about workflows, executions, users, and credentials, but it can't create, delete, or change anything in your n8n instance.

Create an agent that periodically calls `list_workflow_executions` and filters for a 'failed' status. For each failure, it uses `get_execution_details` to get the error log and then writes that structured JSON payload to Cloud Logging.

Yes, `list_workflow_executions` accepts parameters to filter runs. This is critical for performance, letting your agent request only failed executions or runs for a specific workflow instead of pulling the entire history.

The `list_stored_credentials` tool provides only non-sensitive metadata: the credential's ID, name, type, and timestamps. The actual secrets are never transmitted, and the connection is secured through the Vinkius ephemeral sandbox.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript