How to Use the Aha! MCP in OpenAI Agents SDK

Q: How do I connect Aha! to the OpenAI Agents SDK?

Install openai-agents via pip. Initialize the MCP connection using MCPServerStreamableHttp with your Vinkius URL and pass it to the mcpservers array in your Agent constructor.

Q: Can my OpenAI Agents SDK system cache Aha! responses?

Yes. Set cacheToolsList=True during setup. This prevents your agent from repeatedly fetching the tool schema from the MCP Server on every single run.

Build production-ready product management agents with Aha! and the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aha! MCP to OpenAI Agents SDK

Create your Vinkius account to connect Aha! 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 Aha! with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Aha! roadmaps with OpenAI Agents SDK

Your deployed agents need access to Aha! product strategy without hallucinating roadmap items. Hook up this MCP server and your OpenAI agent instantly pulls active work using `list_releases`. You get full tracing in the OpenAI dashboard. When a specialized agent hands off a task to create a new backlog item via `create_idea`, you see exactly what data was passed.

Guardrails for feature extraction

Production systems cannot afford accidental data leaks when calling the MCP tool `get_feature`. Set up strict safety constraints in your agent constructor before allowing it to touch your roadmap. The SDK automatically discovers available tools. Your agent figures out when to pull feature details and when to stop, keeping your product data strictly within defined boundaries.

Safe idea generation pipelines

Customer feedback flows in, but someone has to log it into Aha!. Build an agent system that reads support tickets and automatically pushes them to your backlog using `list_ideas` to check for duplicates first. If no match exists, the agent triggers `create_idea`. Everything runs through the OpenAI framework's built-in validation checks before a single HTTP request hits the Vinkius endpoint.

Setup guide

Set up Aha! 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 Aha! tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Initialize the MCP connection using `MCPServerStreamableHttp` with your Vinkius URL and pass it to the `mcp_servers` array in your Agent constructor.

Yes. Set `cacheToolsList=True` during setup. This prevents your agent from repeatedly fetching the tool schema from the MCP Server on every single run.

The agent automatically maps five tools. It reads existing work via `list_features` or pushes new concepts through `create_idea` without manual tool definition.

They do. You can have a triage agent read incoming feedback and hand off to a product manager agent that actually calls the Aha! endpoint to log it.

Your strategic goals and release schedules stay isolated. Vinkius runs the integration inside an ephemeral V8 sandbox, meaning your ideas and feature descriptions pass through a zero-trust environment that shuts down immediately after the agent finishes its request.

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