How to Use the Kameleoon MCP in LangChain

Q: Can LangChain agents create Kameleoon experiments automatically?

Yes. Your agent can execute createexperiment as long as it has the required name and site ID. You just need to provide the logic for when it should trigger.

Q: How does the Kameleoon MCP Server handle asynchronous results?

The getexperimentresults tool initiates an async process in the API. Your agent needs to be prompted to check back or handle the delayed response appropriately.

Build multi-step experimentation chains with LangChain. Connect A/B tests directly to your broader data pipelines 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 LangChain

Create your Vinkius account to connect Kameleoon to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain your Kameleoon MCP Server into LangChain

Your agent doesn't just run an isolated API call. It pulls active tests using `list_experiments`, checks the variations via `list_variations`, and feeds that context directly into downstream tools. You get a sequence where the output of one step drives the next. That means you can tie A/B testing directly to your analytics warehouse or Slack notifications. The agent checks `get_experiment_results` and triggers an alert if a variation tanks your conversion rate.

Automate experiment provisioning

Manual setup kills momentum. You can script a LangChain agent to read a Jira ticket and immediately fire `create_experiment` to spin up the test. It assigns the correct site ID grabbed from `list_sites` without human intervention. Then it configures the targeting. The agent calls `list_targeting_rules` and `list_segments` to map the right audience to the new test. You bypass the UI completely and launch faster.

Full observability via LangSmith

You need to know exactly what your agent is doing with your testing data. Because this runs through standard tools, LangSmith logs every single `get_site` and `get_experiment` payload. If an agent misconfigures a test, you catch it in the trace. You see the exact token usage, latency, and inputs sent to the `list_custom_data` endpoint. No guessing why a test targeted the wrong segment.

Setup guide

Set up Kameleoon MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kameleoon tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kameleoon-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kameleoon transactions"
    })
    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 LangChain

Use the langchain-mcp-adapters package. You pass your server URL into MultiServerMCPClient and call get_tools() to bind them to your agent.

Yes. Your agent can execute create_experiment as long as it has the required name and site ID. You just need to provide the logic for when it should trigger.

The get_experiment_results tool initiates an async process in the API. Your agent needs to be prompted to check back or handle the delayed response appropriately.

You can restrict the agent's actions or require human-in-the-loop approval before it saves changes. LangSmith traces will also show you exactly which segment it attempted to apply.

The server only accesses the specific A/B test configurations, audience segments, and campaign metrics you expose. Auth tokens stay local to your environment, meaning your raw user traffic data never leaks into the LLM provider's training sets.

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