How to Use the Kameleoon MCP in Claude Code

Q: How do I configure the Kameleoon MCP for Claude Code?

Run claude mcp add --transport http kameleoon -- . Make sure all flags come before the server name. Your configuration saves directly to /.claude.json.

Q: Can I use Claude Code to check Kameleoon results in CI?

Yes. You can script the agent to call getexperimentresults during your build process. Just account for the asynchronous delay in your pipeline timeout settings.

Q: Does this work for multi-site Kameleoon setups?

It absolutely does. The integration exposes listsites and getsite. Your terminal agent can easily switch context between different domains or environments.

Orchestrate Kameleoon experiments straight from your terminal or CI/CD pipeline using Claude Code.

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 Code

Create your Vinkius account to connect Kameleoon to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Claude Code MCP Server Automation

This MCP server lets you script your entire testing infrastructure from the command line. Terminal users hate web dashboards for a reason. You can now control deployments by piping commands through this integration, running `list_sites` to grab your environment IDs during a build pipeline. Once the pipeline has the ID, it triggers `create_experiment` automatically. You get programmatic A/B tests spun up the second your staging branch merges, without a single manual click.

Terminal-Native Experiment Audits

You can audit campaign statuses across multiple environments using simple terminal commands. Checking these manually is a nightmare. Drop a simple script in your CLI that loops through `list_experiments` to output a clean text table of everything currently running. If something looks wrong, dig deeper instantly. You can fire `get_experiment` followed by `list_targeting_rules` to dump the exact JSON configuration right to stdout. Fixing broken tests becomes a standard grep operation.

Headless Results Extraction

Your CLI agent can extract headless results data without manual CSV exports. Data analysts usually pull reports by hand. You can bypass that entirely by having your agent hit `get_experiment_results` on a cron job. The API handles the asynchronous report generation. Your script just waits for the payload, then uses `list_variations` to map the metrics back to the specific code branches before pushing the summary to Slack.

Setup guide

Set up Kameleoon MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see kameleoon-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Kameleoon transactions." It will automatically discover and invoke the available Kameleoon tools.

Terminal

claude mcp add --transport http kameleoon-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Kameleoon MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "kameleoon-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add --transport http kameleoon -- `. Make sure all flags come before the server name. Your configuration saves directly to `~/.claude.json`.

Yes. You can script the agent to call `get_experiment_results` during your build process. Just account for the asynchronous delay in your pipeline timeout settings.

It absolutely does. The integration exposes `list_sites` and `get_site`. Your terminal agent can easily switch context between different domains or environments.

You can connect using stdio, http, or sse. Headless environments usually prefer http for remote execution.

Vinkius wraps your targeting rules in an isolated sandbox that spins down immediately after the command exits. We handle the authentication securely so your terminal only deals with a temporary MCP token, keeping the actual API keys off your local machine.

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