Can I search for failed workflows across my entire history?

Yes. The search tool supports Elasticsearch query syntax — search by status (FAILED, TIMED_OUT), workflow type, date ranges, or correlation IDs. Ask your agent 'show me all failed workflows from the last 24 hours' and it returns matching executions with their IDs, failure reasons, and timestamps.

What's the difference between workflow definitions and running instances?

Definitions are the blueprints — the graph schema with tasks, operators, and branching logic. Running instances are actual executions of those definitions, each with their own input data, current state, and task-by-task progress. Think of definitions as classes and instances as objects.

Does this integration support triggering new workflow executions?

Currently, this integration focuses on observability — listing definitions, monitoring running instances, and searching execution history. It does not trigger new workflow executions. For launching workflows, use the Orkes Conductor UI or direct API calls.

Orkes Conductor MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: Orkes Conductor
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Orkes Conductor through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Orkes Conductor Assistant",
            instructions=(
                "You help users interact with Orkes Conductor. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Orkes Conductor"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Orkes Conductor MCP Server

Connect your Orkes Conductor cluster to any AI agent and get full visibility into your workflow orchestration layer — definitions, running instances, task states, and execution history.

The OpenAI Agents SDK auto-discovers all 6 tools from Orkes Conductor through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Orkes Conductor, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Workflow Definitions — List all registered workflow definitions with versions and descriptions, or inspect a specific workflow's graph schema with tasks, operators, and branching logic
Task Definitions — List all registered task definitions available for orchestration within your workflows
Running Instances — List actively running workflow instances filtered by workflow name to monitor what's currently executing
Execution Details — Get deep state details for any workflow execution including input/output mappings, task-by-task trace histories, and exceptions
Workflow Search — Search across all workflow executions using Elasticsearch queries, filtering by status, correlation ID, or workflow type

The Orkes Conductor MCP Server exposes 6 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Orkes Conductor to OpenAI Agents SDK via MCP

Follow these steps to integrate the Orkes Conductor MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 6 tools from Orkes Conductor

Why Use OpenAI Agents SDK with the Orkes Conductor MCP Server

OpenAI Agents SDK provides unique advantages when paired with Orkes Conductor through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Orkes Conductor + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Orkes Conductor MCP Server delivers measurable value.

Automated workflows: build agents that query Orkes Conductor, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Orkes Conductor, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Orkes Conductor tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Orkes Conductor to resolve tickets, look up records, and update statuses without human intervention

Orkes Conductor MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect Orkes Conductor to OpenAI Agents SDK via MCP:

get_execution

Get deep state details of a specific Workflow Execution

get_workflow_def

Get a specific Workflow Definition explicitly by name

list_running

List active, running workflow instances by explicit workflow name

list_task_defs

List all explicitly registered Task Definitions via Conductor API

list_workflow_defs

List all registered overarching Workflow Definitions via Orkes API

search_workflows

Perform an elastic Search across all Workflow executions

Example Prompts for Orkes Conductor in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Orkes Conductor immediately.

"Show me all registered workflow definitions."

"Are there any failed workflows in the last 24 hours?"

"How many instances of the order-processing workflow are currently running?"

Troubleshooting Orkes Conductor MCP Server with OpenAI Agents SDK

Common issues when connecting Orkes Conductor to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Orkes Conductor + OpenAI Agents SDK FAQ

Common questions about integrating Orkes Conductor MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.