How to Use the Relay Workflow Automation MCP in OpenAI Agents SDK

Trigger and monitor Relay Workflow Automation runs natively inside your production OpenAI Agents SDK pipelines with 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 OpenAI Agents SDK

Create your Vinkius account to connect Relay Workflow Automation to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Discover and run workflows with OpenAI Agents SDK

The `list_workflows` tool lets your OpenAI Agents SDK setup scan your active Relay account to find available automations before starting executions. Once your agent identifies the correct automation, it uses `run_workflow` to pass the required input variables as a clean JSON object and kick off the execution immediately. This setup means your OpenAI agents do not have to guess parameter structures. The OpenAI Agents SDK reads the tool schema directly, matches the schema against the agent's context, and triggers the run without manual coding or hardcoded endpoints.

Cancel stale runs via OpenAI dashboard tracing

The `cancel_run` tool stops any active workflow execution that is taking too long or hitting unexpected errors during an agent run. Your agent checks the execution state with `get_run_status` and triggers a cancellation if a step hangs or if a human operator flags an issue in the OpenAI Agents SDK tracing dashboard. This gives your deployed Python agents a built-in safety valve. Instead of letting stuck processes consume your API quota, the agent detects the delay and terminates the run to keep your execution pipelines clean.

Track execution runs with this MCP Server

The `list_runs` tool provides a history of recent executions so your OpenAI Agents SDK agent can verify past run data before starting a new step. If a previous run succeeded, the agent extracts the output parameters using `get_workflow` to chain the data into the next step of your agent handoff. Using this MCP Server ensures that every step of your Relay automation is fully visible to the OpenAI tracing dashboard. You see exactly when a workflow was triggered, what variables were passed, and when it finished.

Setup guide

Set up Relay 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 Relay Workflow Automation tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Relay 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 Relay 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="Relay Workflow Automation Agent",
            instructions="You have access to Relay 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 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 OpenAI Agents SDK

Install the python package and initialize the streaming server class with your Vinkius endpoint. Pass that instance into your agent's server list to enable auto-discovery of all execution tools.

No, the agent must check the workflow schema first. It uses the listing tool to read required parameters and builds the JSON payload dynamically.

Your agent polls the run status at set intervals. If a run stalls, the agent invokes the cancel tool to terminate the process and prevent resource waste.

Yes, you can filter the tools exposed to the Agent constructor. This limits the agent to read-only actions or full execution actions as needed.

Vinkius manages your Relay API tokens in an ephemeral, zero-trust MCP environment. Your workflow inputs and execution parameters are processed directly through the OpenAI Agents SDK stream without persistent logging on Vinkius servers.

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