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

Q: How do I connect the Make (Workflow Automation) MCP Server to Google ADK?

Set up the connection using McpToolset(serverparams=StreamableHttpServerParameters(url="...")). Then pass this toolset to your LlmAgent initialization via the tools parameter. It supports both Stdio and HTTP transports.

Q: Do I need to expose all Make (Workflow Automation) tools to Google ADK?

No. You control the exact surface area. Use the toolnames filter in your setup to restrict the agent to specific operations like getscenario or listdatastores.

Q: How does the agent know which team owns a workflow?

It starts by calling listorganizations to get the base ID. Then it runs listteams to map the internal structure. Finally, it fetches the specific scenarios for that team.

Give your Google ADK agents direct access to the Make (Workflow Automation) MCP Server to audit scenarios and analyze logs at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Make (Workflow Automation) MCP to Google ADK

Create your Vinkius account to connect Make (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 Make (Workflow Automation) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Make (Workflow Automation) logs to Google ADK

Gemini's massive context window changes how you debug automations using `list_scenario_logs`. You can dump thousands of lines of execution history straight into the agent. It reads the whole timeline and finds the exact moment a workflow started failing. This MCP Server connects your automation infrastructure directly to Google Cloud. Your agent uses `get_scenario` to read the blueprint, then cross-references that structure against historical log data to spot logic errors.

Audit scenarios and team structures

Managing large Make deployments gets messy fast, but your agent runs `list_organizations` to map the environment. It follows up with `list_teams` to build a complete directory of your automation workspaces. It maps out exactly where every scenario lives. You can filter the noise by restricting the tools this MCP Server exposes. If you only want the agent to monitor active workflows, pass a `tool_names` filter to your setup so it only sees `list_scenarios`.

Monitor connections and data stores

Broken third-party auth causes most automation failures, so the agent calls `list_connections` to verify linked apps. It checks which services connect to your workspaces. If a token expires, the agent knows before the next scheduled run. Temporary storage needs oversight too. By running `list_data_stores`, the agent checks the databases your scenarios use for state management. You get full visibility into the underlying architecture without leaving your Vertex AI environment.

Setup guide

Set up Make (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 Make (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="Make (Workflow Automation)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Make (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 Make. 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 Make (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 Make (Workflow Automation) MCP in Google ADK

Set up the connection using `McpToolset(server_params=StreamableHttpServerParameters(url="..."))`. Then pass this toolset to your `LlmAgent` initialization via the `tools` parameter. It supports both Stdio and HTTP transports.

Yes. Gemini's massive context window easily handles large log dumps. You can pull extensive histories using `list_scenario_logs` and ask the agent to find hidden patterns.

No. You control the exact surface area. Use the `tool_names` filter in your setup to restrict the agent to specific operations like `get_scenario` or `list_data_stores`.

It starts by calling `list_organizations` to get the base ID. Then it runs `list_teams` to map the internal structure. Finally, it fetches the specific scenarios for that team.

The integration only reads scenario metadata and execution histories from your workspaces. Google ADK routes the requests through your secure HTTP transport. This ensures your Make API tokens never touch the LLM directly.

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