How can I check if an experiment is currently active on a specific site?

Use the `list_experiments` tool to get a summary of all experiments, which includes their current status (e.g., 'ACTIVE', 'PAUSED') and assigned site IDs.

Can I see the defined variations for a particular experiment?

Yes, the `list_variations` tool takes an experiment ID and returns all variants configured for that test, along with their metadata.

Is it possible to list targeting rules and segments?

Absolutely. You can use the `list_segments` and `list_targeting_rules` tools to inspect how your traffic is being allocated across your experimentation ecosystem.

Kameleoon MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Kameleoon
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Kameleoon through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Kameleoon "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Kameleoon?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Kameleoon MCP Server

Empower your AI agents to control your Kameleoon experimentation platform. This MCP server enables seamless management of experiments, variations, and audience segments directly from natural language interfaces.

Pydantic AI validates every Kameleoon tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Experiment Control — List all active experiments and drill down into specific configurations and metadata
Variation Management — Inspect A/B variations and their statuses across different digital properties
Site Inventory — Query all sites and properties registered in your account to ensure correct environment targeting
Audience Segmentation — List defined audience segments and targeting rules used for precise traffic allocation
Results Triggering — Request latest results reports to analyze experiment performance on the fly

The Kameleoon MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Kameleoon to Pydantic AI via MCP

Follow these steps to integrate the Kameleoon MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Kameleoon with type-safe schemas

Why Use Pydantic AI with the Kameleoon MCP Server

Pydantic AI provides unique advantages when paired with Kameleoon through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Kameleoon integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Kameleoon connection logic from agent behavior for testable, maintainable code

Kameleoon + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Kameleoon MCP Server delivers measurable value.

Type-safe data pipelines: query Kameleoon with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Kameleoon tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Kameleoon and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Kameleoon responses and write comprehensive agent tests

Kameleoon MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Kameleoon to Pydantic AI via MCP:

create_experiment

Requires a name and a site ID. Create a new experiment

get_experiment

Get details for a specific experiment

get_experiment_results

This is an asynchronous process in the Kameleoon API. Request a results report for an experiment

get_site

Get details for a specific site

list_custom_data

List custom data dimensions

list_experiments

Use this to monitor campaign statuses and identify active experiments. List all experiments in Kameleoon

list_segments

List audience segments

list_sites

List all sites in the account

list_targeting_rules

List targeting rules

list_variations

) associated with a specific experiment ID. List variations for an experiment

Example Prompts for Kameleoon in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Kameleoon immediately.

"Show me all active experiments in my Kameleoon account."

"What are the variations for experiment ID '12345'?"

"List all sites registered in my Kameleoon profile."

Troubleshooting Kameleoon MCP Server with Pydantic AI

Common issues when connecting Kameleoon to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Kameleoon + Pydantic AI FAQ

Common questions about integrating Kameleoon MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Kameleoon MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.