How to Use the Kameleoon MCP in OpenAI Agents SDK

Q: How do I connect the Kameleoon MCP Server to the OpenAI Agents SDK?

Install the package and initialize the MCPServerStreamableHttp class with your endpoint. Pass that into your agent constructor to let the SDK auto-discover all available tools.

Q: Can the OpenAI Agents SDK handle Kameleoon experiment results?

Yes. You trigger getexperimentresults through the agent and it processes the return data. The SDK handles the tool execution flow while you focus on the logic.

Q: How do I list variations for an experiment in the OpenAI Agents SDK?

Call listvariations with your specific experiment ID. The server returns the list of variations, which your agent can then iterate over or analyze.

Control your A/B testing cycles directly through the OpenAI Agents SDK with the Kameleoon MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kameleoon MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate experiment lifecycle management

Stop manual setup in the web dashboard. Use `create_experiment` to push new tests directly from your deployment pipeline. You can keep track of campaign health by calling `list_experiments` to verify which variations are currently live.

Validate experiment performance with your agent

Your agent fetches raw performance numbers using `get_experiment_results`. It pulls the data directly into your decision loop. Since this happens asynchronously, the agent handles the report request and parses the output without blocking your other tasks.

Inspect audience targeting rules

You can audit how your site segments are built by using `list_segments` and `list_targeting_rules`. This gives your agent the context it needs to confirm that the right users see the right variations before you deploy changes.

Setup guide

Set up Kameleoon 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 Kameleoon tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package and initialize the `MCPServerStreamableHttp` class with your endpoint. Pass that into your agent constructor to let the SDK auto-discover all available tools.

Yes. You trigger `get_experiment_results` through the agent and it processes the return data. The SDK handles the tool execution flow while you focus on the logic.

The server will return an error response which the agent catches. You should implement a retry policy or a delay in your agent logic to respect the API thresholds.

Call `list_variations` with your specific experiment ID. The server returns the list of variations, which your agent can then iterate over or analyze.

The server only touches your account configuration, site IDs, and experiment metadata. It does not store your site traffic or visitor PII, keeping your sensitive data within your own infrastructure.

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