How to Use the Kameleoon MCP in Claude

Q: How do I install the Kameleoon MCP Server on Claude Desktop?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers key. Restart the desktop app, and you will see the tools ready to use in your next chat session.

Q: How does Claude Desktop handle async requests from Kameleoon?

When you ask for analytics, the desktop client calls getexperimentresults and waits for the payload. Once the data is ready, the agent formats the variations and conversion metrics directly inside your chat window.

Q: Can I manage multiple web properties with this setup?

You can query different domains by using listsites and getsite directly inside your conversation. The agent will pull the specific metadata for each site to ensure you are editing the correct workspace.

Command your Kameleoon optimization pipeline from Claude Desktop with this MCP Server to spin up experiments and pull analytics.

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 Claude Desktop

Create your Vinkius account to connect Kameleoon to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Kameleoon experiments from Claude Desktop

Generate new test structures inside your chat window using `create_experiment` without ever loading the web dashboard. You supply the site ID and name, and the tool configures the container instantly so you can start planning your front-end variations. Checking your parameters takes only a second. Your agent triggers `get_experiment` to verify that your test configuration matches your deployment plans before you write any code.

Audit active user segments in your chat window

Audit your active user segments by running `list_targeting_rules` and `list_segments` directly inside your desktop chat. By mapping out these criteria, you verify exactly which visitors see your new variations before pushing code changes live. Cross-referencing these rules with your analytics setup prevents tracking gaps. The tool calls `list_custom_data` to confirm your tracking keys align with your active targeting parameters.

Pull live experiment results on demand

Fetch your raw conversion metrics using `get_experiment_results` instead of dealing with manual CSV exports. This lets you monitor performance metrics and significance levels directly inside your conversation. Because this process is asynchronous, your agent monitors the job and presents the clean numbers in your chat. It uses `list_variations` to map those metrics directly to your design changes.

Setup guide

Set up Kameleoon MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Kameleoon MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Kameleoon MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under kameleoon-mcp.

json

{
  "mcpServers": {
    "kameleoon-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under the `mcpServers` key. Restart the desktop app, and you will see the tools ready to use in your next chat session.

Yes, you can connect the server to the web version of the client by adding the remote server URL under your integration settings. This lets you run tools like `list_experiments` on any machine without local installation.

When you ask for analytics, the desktop client calls `get_experiment_results` and waits for the payload. Once the data is ready, the agent formats the variations and conversion metrics directly inside your chat window.

You can query different domains by using `list_sites` and `get_site` directly inside your conversation. The agent will pull the specific metadata for each site to ensure you are editing the correct workspace.

This setup only transmits your optimization metadata, including experiment names, targeting rules, and variation configurations. Your raw subscriber databases and personal customer identifiers are never exposed or processed by the server.

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