How to Use the Kameleoon MCP in Mastra AI

Q: How do I register the Kameleoon tools inside a Mastra AI agent?

Install @mastra/mcp and instantiate the MCPClient pointing to your Vinkius server URL. Call mcpClient.listTools() and spread them directly into your agent's tool array. Mastra handles transport negotiation automatically.

Q: Can Mastra AI handle human approvals for Kameleoon experiments?

Yes, you can enable the requireToolApproval setting on sensitive tools like createexperiment. This forces the workflow to pause and wait for an admin's green light before launching a test.

Automate your Kameleoon experiment workflows and conditional targeting with Mastra AI agents.

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 Mastra AI

Create your Vinkius account to connect Kameleoon to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build self-healing experiment setups using Mastra AI

`create_experiment` serves as the entry point for your automated testing pipelines. Connecting this MCP Server to Mastra allows your agent to provision new tests instantly. The system immediately calls `get_experiment` to verify the setup succeeded. This hands-off approach ensures your dev pipelines don't stall when external APIs experience minor hiccups.

Branch your targeting logic with this MCP Server

`list_targeting_rules` allows your Mastra agent to inspect who is eligible for active campaigns. The workflow engine uses this data to run conditional branching, routing users based on their segment profile. By calling `list_segments` and `list_custom_data`, the agent evaluates complex user traits before modifying any live rules. You write the logic in TypeScript, and Mastra executes the multi-step verification automatically.

Auto-pause losing variations based on live data

`get_experiment_results` provides the raw performance metrics your agent needs to evaluate a test's success. Mastra processes these results asynchronously to determine if a variant is degrading user experience. If a variation drops below your conversion threshold, the agent uses `list_variations` to isolate the problem. The workflow then alerts your team or pauses the experiment, preventing bad code from hurting your revenue.

Setup guide

Set up Kameleoon MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Kameleoon tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "kameleoon-mcp-client",
  servers: {
    "kameleoon-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Kameleoon Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Kameleoon tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Kameleoon transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp` and instantiate the `MCPClient` pointing to your Vinkius server URL. Call `mcpClient.listTools()` and spread them directly into your agent's tool array. Mastra handles transport negotiation automatically.

Yes, you can enable the `requireToolApproval` setting on sensitive tools like `create_experiment`. This forces the workflow to pause and wait for an admin's green light before launching a test.

Mastra's built-in workflow engine natively supports rate limiting and retry backoffs. When tools like `get_experiment_results` hit upstream rate limits, the framework queues the calls and retries them safely.

Absolutely, you can deploy your Mastra agents to any cloud provider with a single command. The MCP connection remains secure, utilizing Vinkius's managed token system for authentication.

Your site configurations, experiment metadata, and variation setups are processed purely in-memory during workflow execution. Mastra AI does not persist this data externally. All communication with Vinkius runs through isolated, encrypted channels.

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