How to Use the Kameleoon MCP in LlamaIndex

Index your Kameleoon experiments directly into LlamaIndex. Query your A/B testing history with grounded, factual RAG using 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 LlamaIndex

Create your Vinkius account to connect Kameleoon to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index your Kameleoon MCP Server data

LlamaIndex treats your testing data as a live knowledge base. Instead of just pulling metrics, your agent runs `list_experiments` and `get_experiment_results`, then embeds that data into a vector store. Now you can ask your agent what worked last quarter. It searches the index, finds the exact variations from `list_variations`, and gives you an answer grounded in real performance data, not hallucinations.

Query audience and segment definitions

Marketing teams forget how segments are defined. You can point LlamaIndex at `list_segments` and `list_targeting_rules` to build a semantic map of your entire audience structure. When a PM asks which segment targets mobile users in Canada, the agent just queries the vector store. It pulls the exact logic from `list_custom_data` and explains the setup in plain English.

Grounded experiment creation

Creating a new test requires context. Before calling `create_experiment`, your LlamaIndex agent can search past tests to make sure you aren't duplicating an old, failed idea. It verifies the site structure using `list_sites` and `get_site` to ensure the new configuration matches your current architecture. Every decision is backed by the indexed reality of your environment.

Setup guide

Set up Kameleoon MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Kameleoon MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Kameleoon tools.",
)
response = await agent.run("List recent Kameleoon data")

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 LlamaIndex

Install llama-index-tools-mcp. You set up a BasicMCPClient, pass it to McpToolSpec, and use to_tool_list_async() to feed the tools to your FunctionAgent.

Yes. You can configure your agent to periodically fetch data using list_experiments and embed the results. This creates a persistent, searchable history of your testing program.

The MCP standard gives LlamaIndex native understanding of the tool schemas. You skip writing custom wrappers for the API and immediately start querying your test variations and rules.

Not if you configure your RAG pipeline correctly. By forcing the agent to cite data pulled from get_experiment_results, you tie its answers to actual API responses.

The system processes your custom data dimensions and variation code locally. Your API credentials remain isolated in your own infrastructure, so external vector databases only store the embeddings you explicitly authorize.

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