How to Use the ONES MCP in OpenAI Agents SDK

Q: Can I use OpenAI Agents SDK guardrails to control ONES ticket updates?

Yes, you can write validation hooks that intercept updatetask calls. This ensures your agent never changes a ticket status without verifying the transition is valid. It keeps your project board clean and prevents automated mess-ups.

Q: Does OpenAI Agents SDK support caching for ONES MCP tools?

Yes, setting cacheToolsList=True in your server configuration prevents unnecessary schema requests. This keeps your agent fast when it repeatedly checks listtasks or gettaskdetails across large ONES backlogs.

Q: How does the OpenAI agent know which developer to assign a task to?

The agent queries listmembers to get the correct user IDs from your organization. It matches the developer's name or email to the ID and passes it directly to createtask.

Control your entire ONES R&D backlog directly from OpenAI Agents SDK with strict guardrails and automated task creation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ONES MCP to OpenAI Agents SDK

Create your Vinkius account to connect ONES 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 ONES with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate task changes with OpenAI Agents SDK

Let your OpenAI agent inspect the current ONES sprint status using `get_project` and `get_task_details` before making changes. The agent gathers exact context on what developers are working on. This prevents the agent from creating duplicate work or editing the wrong ticket. You can set up strict guardrails to analyze the output of `update_task` before it hits your production tracker. If the agent tries to move a ticket to an invalid state, the SDK catches the error, looks up valid states via `list_workflows`, and corrects the action automatically.

Automate ticket creation via specialized agent handoffs

Break down complex feature requests into actual tracking items using `create_task` without manual typing. One OpenAI agent can parse a raw engineering document, while a specialized ticketing agent builds the items in your ONES backlog. During this process, the agent pulls valid options using `list_task_types` and `list_members` to assign the work to the right team member. The whole flow runs asynchronously, with every step tracked on your OpenAI dashboard so you can audit what the agent did.

Auto-discover ONES MCP Server tools with zero config

Stop writing custom API wrappers when the OpenAI Agents SDK discovers the tools exposed by this MCP server automatically, enabling immediate access to `list_projects` and `get_org_info`. To keep performance high, enable tool caching so your agent doesn't waste network roundtrips fetching schemas. It gets the speed of local execution while maintaining a direct connection to your live ONES R&D data.

Setup guide

Set up ONES 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 ONES tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ONES 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="ONES Agent",
            instructions="You have access to ONES 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 ONES. 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 ONES 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 ONES MCP in OpenAI Agents SDK

Install the package and configure the streamable HTTP transport using `MCPServerStreamableHttp`. Pass this instance inside the `mcp_servers` list when initializing your agent. The agent will auto-discover the project management tools immediately.

Yes, you can write validation hooks that intercept `update_task` calls. This ensures your agent never changes a ticket status without verifying the transition is valid. It keeps your project board clean and prevents automated mess-ups.

Yes, setting `cacheToolsList=True` in your server configuration prevents unnecessary schema requests. This keeps your agent fast when it repeatedly checks `list_tasks` or `get_task_details` across large ONES backlogs.

The agent queries `list_members` to get the correct user IDs from your organization. It matches the developer's name or email to the ID and passes it directly to `create_task`.

Your tasks, workflows, and org structure data remain inside an ephemeral V8 sandbox managed by Vinkius. No project details are stored on the host, and all API calls require a single secure endpoint token to execute.

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