How to Use the Relay Workflow Automation MCP in Google ADK

Run enterprise Relay Workflow Automation tasks directly from Gemini models using the Google ADK toolset integrations using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Relay Workflow Automation MCP to Google ADK

Create your Vinkius account to connect Relay Workflow Automation to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Relay Workflow Automation with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Pull BigQuery data to trigger Relay runs

The `run_workflow` tool executes specific Relay automations using variables fetched directly from your BigQuery tables or Vertex AI pipelines within the Google ADK. Your Gemini agent reads the database state, formats the parameters, and fires the workflow to sync your Google Cloud data with external systems. Because the Google ADK supports deep context, your Gemini agent can analyze thousands of rows of cloud data before deciding which variables to send. This makes your automated triggers highly accurate and grounded in your live cloud database.

Scan and audit runs within Google ADK pipelines

The `list_runs` tool retrieves the execution history of your automations so your Google ADK agent can audit recent activities. The Gemini agent checks the status of each run using `get_run_status` to ensure no errors occurred during critical data syncs. If a run failed, the agent extracts the configuration details with `get_workflow` to diagnose the root cause. It can then log the error directly to Google Cloud Logging or attempt a clean retry within the Google ADK pipeline.

Control active executions using this MCP Server

The `cancel_run` tool stops active executions that do not meet your business rules or that exceed budget limits in your Google ADK environment. Your Gemini agent evaluates current run parameters and triggers a cancel request if it detects anomalous behavior. This MCP Server integration allows you to filter which tools are exposed to the Google ADK using the tool names parameter. You can restrict your agent to monitoring tools like `list_workflows` or grant full execution rights as needed.

Setup guide

Set up Relay 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 Relay 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="Relay Workflow Automation_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Relay 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 Relay. 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 Relay 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 Relay Workflow Automation MCP in Google ADK

Use the toolset class with your Vinkius HTTP endpoint inside your Python code. Pass the toolset object directly into the tools list when initializing your agent.

Yes, the agent calls the listing tool to find all active automations in your account. It then uses Gemini's reasoning to match the correct workflow to your request.

Your agent uses the status tool to monitor the execution state. If it catches a failure, you can program the agent to pull run details and generate a report.

Yes, you can use the tool name filter in the server parameters to expose only safe tools and exclude destructive ones.

Your Relay API credentials reside securely within the Vinkius zero-trust MCP environment. Workflow execution data and status payloads pass directly to your Google Cloud environment without being cached or stored.

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