How to Use the Make (Workflow Automation) MCP in OpenAI Agents SDK

Q: How do I use the Make (Workflow Automation) MCP Server with OpenAI Agents SDK?

Initialize it via MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="...")). Pass that server into your agent constructor using mcpservers=server. Set cacheToolsList=True to speed up auto-discovery.

Q: How do I find the right organization ID?

Have your agent run listorganizations first. This returns the IDs for the authenticated user. You then pass those IDs into tools like listscenarios or listteams.

Connect the Make (Workflow Automation) MCP Server directly to OpenAI Agents SDK to track execution logs and debug errors in production.

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 OpenAI Agents SDK

Create your Vinkius account to connect Make (Workflow Automation) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Make (Workflow Automation) via OpenAI Agents SDK

Your agent needs visibility into your automation infrastructure using `list_organizations` and `list_teams`. By equipping it with the Make (Workflow Automation) MCP Server, it pulls exact configurations straight from your account. This gives the agent a complete map of who owns what across your company. You don't have to guess if a workflow is active. The agent calls `list_scenarios` to pull IDs and statuses directly into its context window. From there, OpenAI's built-in tracing tracks exactly which tools the agent called and when.

Debug execution failures instantly

Silent failures in automation chains cost money, so your agent runs `get_scenario` to check the setup when a webhook drops. It then pulls the actual error trace using `list_scenario_logs`. It reads the raw output instead of relying on a generic dashboard alert. Handoffs between specialized agents fix this fast. One agent monitors the logs for timeouts, and if it finds one, it passes the exact error payload to a debugging agent. You patch the logic before the client even notices the drop.

Map connections and data stores

Automations rely on external credentials, which your agent checks via `list_connections`. It sees exactly which third-party apps are linked to an organization. If a connection drops, the agent flags it immediately through the OpenAI dashboard. State management requires oversight too. This MCP Server reveals the custom databases your scenarios use to hold variables between runs via `list_data_stores`. Your agent reads this architecture and validates that data is actually moving where it belongs.

Setup guide

Set up Make (Workflow Automation) MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Make (Workflow Automation) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Make (Workflow Automation) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Make (Workflow Automation) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Make (Workflow Automation) Agent",
            instructions="You have access to Make (Workflow Automation) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Initialize it via `MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="..."))`. Pass that server into your agent constructor using `mcp_servers=[server]`. Set `cacheToolsList=True` to speed up auto-discovery.

No. The available tools focus strictly on auditing and monitoring. Your agent can read configurations via `get_scenario` and pull execution data, but it cannot write new workflows.

Yes. You define safety constraints before the agent executes any tool. If the agent tries to pull `list_scenario_logs` for an unauthorized organization, the guardrail blocks the request.

Have your agent run `list_organizations` first. This returns the IDs for the authenticated user. You then pass those IDs into tools like `list_scenarios` or `list_teams`.

The server reads scenario configurations, execution logs, and data store schemas. Your endpoint token restricts access strictly to the Make organizations you authorize. This keeps all API keys and payload contents isolated from the agent runtime.

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