How to Use the Kippy MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK connect to Kippy?

You just need your Vinkius endpoint URL. Instantiate an MCPServerStreamableHttp object with the URL and pass it to your agent's constructor. The SDK automatically discovers all the Kippy tools from the MCP server like listteams and listkpis.

Build production-ready agents with the OpenAI Agents SDK to manage team performance data from your Kippy server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kippy MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get real-time answers on team performance

Your agent can instantly pull performance data for any team or individual. Ask it to `list_team_scores` for the quarter or `list_annual_scores` for a specific department. The agent gets the raw numbers from Kippy and gives you a straight answer. You can also dig into the specifics. Use `list_appraisals` to see recent reviews or `list_feedback` to check on peer comments. The OpenAI agent handles the API calls; you just ask the questions.

Automate performance reporting with your MCP Server

Stop manually pulling reports. Build an agent that regularly checks on key metrics using `list_kpis` and `list_kpi_scores`. You can set up workflows where one agent monitors KPIs and hands off to another agent to flag anomalies. This OpenAI Agents SDK server integration makes it simple. The agent discovers the Kippy tools automatically. You just define the mission, and it uses tools like `list_projects` and `list_project_scores` to assemble the data you need for your weekly updates.

Audit system activity with agent guardrails

Connect an agent to track system changes and user activity. It can use `list_audit_logs` to monitor events and `list_users` to cross-reference who did what. This gives you a live feed of important actions inside Kippy. The OpenAI SDK's built-in guardrails are key here. You can configure rules to prevent the agent from taking unintended actions, adding a layer of safety when dealing with sensitive audit and performance data. It's about getting answers without giving up control.

Setup guide

Set up Kippy 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 Kippy tools at runtime.
3

Create your Agent

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

Run the agent

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

You just need your Vinkius endpoint URL. Instantiate an `MCPServerStreamableHttp` object with the URL and pass it to your agent's constructor. The SDK automatically discovers all the Kippy tools from the MCP server like `list_teams` and `list_kpis`.

Yes. While the agent discovers all tools by default, you can implement your own logic and guardrails within your agent's code. This lets you restrict access to sensitive operations like `list_appraisals` based on the user's intent.

You can ask for anything Kippy tracks. For example, 'What are the latest KPI scores for the marketing team?' or 'Show me the project scores for Q3.' Your agent will use the `list_kpi_scores` and `list_project_scores` tools to get the answers.

Not at all. The SDK is designed for this. You can create an agent that uses `list_team_scores` and `list_annual_scores` to compile a summary, then format it into a report without you writing any data-fetching code.

Your data, including employee appraisals and KPI scores, is sent over a secure connection between your agent and the Vinkius-managed server. Vinkius handles the auth and runs the server in an ephemeral sandbox, so your credentials and data aren't stored long-term.

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