How to Use the Kameleoon MCP in AutoGen

Q: How do I load Kameleoon tools into AutoGen?

Use autogen-extmcp. You initialize the tools with mcpservertools and pass that directly into your AssistantAgent constructor.

Build multi-agent systems in AutoGen that debate and manage your Kameleoon A/B tests via this 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 AutoGen

Create your Vinkius account to connect Kameleoon to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect your MCP Server to AutoGen debates

You don't have to rely on one agent's opinion. You can set up a product agent that proposes a test via `create_experiment` while a data agent challenges the sample size. They argue until they reach a consensus. The data agent might pull `list_segments` to prove the target audience is too small. Once they agree, the system executes the final configuration. You get peer-reviewed A/B tests generated entirely by code.

Automated performance monitoring

Assign a dedicated analytics agent to watch your active campaigns. It runs `list_experiments` to find running tests and triggers `get_experiment_results` to evaluate the data. If a test is tanking, it can notify a separate operations agent using the MCP Server. They review the specific changes via `list_variations` and decide whether to pause the campaign or let it run.

Audit targeting rules collaboratively

Complex sites have conflicting personalization rules. You can instruct an AutoGen group chat to map out your logic using `list_targeting_rules` and `list_custom_data`. A security agent checks for privacy risks in the custom data, while a marketing agent verifies the business logic. They fetch site details with `get_site` and `list_sites` to ensure rules are applied to the correct domains.

Setup guide

Set up Kameleoon MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kameleoon tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kameleoon_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kameleoon data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kameleoon_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kameleoon data")
    print(result.messages[-1].content)

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 AutoGen

Use autogen-ext[mcp]. You initialize the tools with mcp_server_tools and pass that directly into your AssistantAgent constructor.

Yes. You can give the testing tools to specific agents in a group chat. One agent handles creation, while another handles querying results.

The server passes through standard API constraints. If your agents spam get_experiment during a debate, they will hit the upstream limits and need to handle the backoff.

Yes, if you give them access to the mutation tools. It is usually best to require human approval in the chat before an agent executes a destructive action.

The integration reads targeting rules and site IDs directly into your local execution environment. The standard ensures that your authentication keys are never exposed to the agents themselves.

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