How to Use the Kameleoon MCP in Vercel AI SDK

Q: How do I connect the Kameleoon MCP Server to the Vercel AI SDK?

Install the @ai-sdk/mcp package and initialize the client using createMCPClient with your Vinkius HTTP endpoint. Pass the tools directly into generateText or streamText to let your agent call them. Remember to call mcpClient.close() when the session ends to prevent memory leaks.

Q: How does Vercel AI SDK handle long-running Kameleoon reports?

The SDK streams the intermediate status of getexperimentresults as the Kameleoon API processes the data. Your agent receives the raw payload and updates the UI progressively. This means your developers never face gateway timeouts on large datasets.

Q: Do I need to manually configure targeting segments?

No, your agent handles that. By using listsegments, the agent reads existing configurations and applies them to new tests. You just tell the agent who to target in plain English.

Run and monitor Kameleoon experiments live in your Next.js frontend with Vercel AI SDK streaming.

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 Vercel AI SDK

Create your Vinkius account to connect Kameleoon to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Launch experiments from the edge using Vercel AI SDK

`create_experiment` lets your agent provision new A/B tests instantly during user interactions or deployment triggers. We bypass the heavy web dashboard entirely so you can roll out variations without leaving your terminal or code editor. When you pair this with `list_sites`, your agent checks active domains to ensure the experiment targets the correct environment. The Vercel AI SDK handles these calls inside edge functions to keep your site fast.

Render targeting rules in real-time with this MCP Server

`list_targeting_rules` exposes the specific criteria controlling who sees which version of your site. Your agent pulls these rules and displays them instantly in your admin dashboard while streaming the response. To refine these audiences, the agent calls `list_segments` and `list_custom_data` to map out user traits. Because the Vercel AI SDK streams the output, developers see these complex JSON structures render on the screen line-by-line instead of staring at a blank loading state.

Stream conversion metrics directly to your screen

`get_experiment_results` triggers an asynchronous report request to fetch the performance data of your active tests. Your agent checks this data to tell you which variant wins. You can also run `list_variations` alongside this to inspect the exact changes under review. This MCP Server setup ensures your product team gets raw numbers without manually exporting CSVs from a third-party platform.

Setup guide

Set up Kameleoon MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Kameleoon tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Kameleoon transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the client using `createMCPClient` with your Vinkius HTTP endpoint. Pass the tools directly into `generateText` or `streamText` to let your agent call them. Remember to call `mcpClient.close()` when the session ends to prevent memory leaks.

Yes, this integration is fully compatible with edge runtimes. The Vercel AI SDK handles the streaming connection efficiently without bloated node-only dependencies. This setup keeps your global response times under 50ms.

The SDK streams the intermediate status of `get_experiment_results` as the Kameleoon API processes the data. Your agent receives the raw payload and updates the UI progressively. This means your developers never face gateway timeouts on large datasets.

No, your agent handles that. By using `list_segments`, the agent reads existing configurations and applies them to new tests. You just tell the agent who to target in plain English.

All custom data dimensions and targeting rules remain inside Vinkius's secure sandbox. The Vercel AI SDK only receives the final structured JSON over an encrypted HTTPS connection. Your user telemetry and PII never pass through external LLM servers.

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