How to Use the Kameleoon MCP in CrewAI

Q: How do I configure my CrewAI agents to use Kameleoon tools?

Pass your Vinkius server URL directly into the agent's mcps parameter during initialization. For complex setups, import MCPServerHTTP from crewai.mcp and apply a toolfilter to restrict specific agents to specific tools.

Run autonomous teams of agents to manage and monitor Kameleoon experiments using CrewAI.

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 CrewAI

Create your Vinkius account to connect Kameleoon to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent testing setups in CrewAI

`create_experiment` is used by your builder agent to provision new tests based on product specifications. Meanwhile, a QA agent uses `get_site` to verify the target domain is active and configured correctly. This team-based approach ensures no test goes live with broken parameters. By separating the creation and validation steps, your autonomous crew acts like a human QA team but operates in seconds.

Map complex audiences using this MCP Server

`list_segments` allows your research agent to scan existing audience profiles across your sites. A separate targeting agent then calls `list_targeting_rules` to map these segments to the correct experiments. They share this context via CrewAI's common memory layer to prevent targeting conflicts. This collaborative loop guarantees that your personalization campaigns never overlap or spam the same user cohort.

Let autonomous agents audit your experiment outcomes

`get_experiment_results` provides the core data feed for your analyst agent to calculate statistical significance. If the results are inconclusive, the agent queries `list_variations` to check if a specific layout is skewing the metrics. Once the analysis is complete, a coordinator agent can recommend next steps or flag anomalies. Running this MCP Server means your team gets clean, summarized reports without having to manually dig through raw telemetry.

Setup guide

Set up Kameleoon MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Kameleoon tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Kameleoon Analyst",
    goal="Access and analyze Kameleoon data via MCP.",
    backstory="Expert analyst with direct Kameleoon access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Kameleoon transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Kameleoon Analyst",
        goal="Access and analyze Kameleoon data via MCP.",
        backstory="Expert analyst with direct Kameleoon access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Kameleoon transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius server URL directly into the agent's `mcps` parameter during initialization. For complex setups, import `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter` to restrict specific agents to specific tools.

Yes, CrewAI supports hierarchical and parallel execution. One agent can fetch custom data via `list_custom_data` while another pulls site details using `list_sites` simultaneously.

CrewAI's shared memory allows agents to pass outputs from tools like `get_experiment` to downstream agents. This ensures your analyst agent knows exactly what the setup agent created.

No, the MCP protocol handles serialization automatically. Your agents receive structured JSON payloads directly from the server, allowing them to extract experiment parameters without custom parsers.

Your site telemetry and custom data dimensions are only processed within your local Python environment. CrewAI does not upload your data to external databases, and the connection to Vinkius is fully encrypted.

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