How to Use the airfocus MCP in OpenAI Agents SDK

Q: What's the best way to handle multiple airfocus workspaces with the OpenAI Agents SDK?

Your agent should first call listairfocusworkspaces to get the ID for each workspace. Then, it can pass the correct workspaceid when calling listairfocusitems or other tools to operate within a specific context.

Build production-ready OpenAI agents that manage your airfocus roadmap with built-in safety checks and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect airfocus MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Your Roadmap from Any Agent

Give your agents direct control over your airfocus product roadmap. They can create new feature ideas with `create_airfocus_item` based on user feedback or update priorities using `update_airfocus_item` after a planning session. Your agent becomes an active participant in your product process. This is where the OpenAI Agents SDK shines. You get built-in guardrails to prevent an agent from making unauthorized changes. Plus, the OpenAI dashboard gives you a full trace, so you can see exactly which agent updated which airfocus item and why. It's control and visibility for production systems.

Give Agents Full Context on Priorities

An agent can't make good decisions without good data. This server lets your agent get a complete picture of your product strategy. It can pull all your backlogs with `list_airfocus_workspaces`, scan every feature idea with `list_airfocus_items`, and check details on a specific task with `get_airfocus_item`. This enables complex, multi-agent workflows. One agent could monitor customer feedback, identify a theme, and use `list_airfocus_items` to see if a similar feature exists. It can then hand off its findings to a different, specialized agent that drafts a new item proposal. You can trace the entire handoff in your dashboard.

Zero-Config MCP Server for Your Agents

Getting started is simple. You just point the OpenAI Agents SDK to the Vinkius server URL. The tools are discovered automatically. Your agent instantly knows how to use `create_airfocus_item` and the rest of the airfocus toolkit without you writing a single line of mapping code. This MCP Server is built for real work, not just demos. Setting `cacheToolsList=True` gives you better performance in production. Vinkius manages the hosting and security, so your agent gets secure, sandboxed access to airfocus and you don't have to worry about managing another piece of infrastructure.

Setup guide

Set up airfocus 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 airfocus tools at runtime.
3

Create your Agent

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

Run the agent

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

It's automatic. When you pass the Vinkius MCP Server endpoint to the Agent constructor, the SDK queries the server to get a list of available tools, like `create_airfocus_item`. You don't have to define them manually.

Yes. The OpenAI Agents SDK is designed with safety in mind. You can implement guardrails in your agent's logic to validate actions before they are executed, effectively creating a custom permission layer for your airfocus tools.

Your agent should first call `list_airfocus_workspaces` to get the ID for each workspace. Then, it can pass the correct `workspace_id` when calling `list_airfocus_items` or other tools to operate within a specific context.

Absolutely. The combination of Vinkius's managed infrastructure and the OpenAI Agents SDK's features like tracing and guardrails is designed for building and deploying production-grade agents.

The server only interacts with your airfocus workspaces, items, and custom field data. All operations run inside an ephemeral V8 Isolate on Vinkius, meaning each request is completely isolated. The OpenAI dashboard also provides a complete audit trail of your agent's actions.

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