How to Use the Chameleon.io MCP in Vercel AI SDK

Q: How do I connect Chameleon.io to Vercel AI SDK?

Install the @ai-sdk/mcp package via npm. You initialize the connection using createMCPClient with your Vinkius HTTP URL. Pass the resulting tools directly into generateText or streamText.

Q: Can Vercel AI SDK stream Chameleon.io microsurvey responses?

Yes, the AI streams the output of listmicrosurveyresponses as it generates the summary. Your React or Vue frontend displays the feedback text chunk by chunk. Users see the analysis immediately.

Stream product adoption data straight into your React frontend using Vercel AI SDK and this Chameleon.io MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chameleon.io MCP to Vercel AI SDK

Create your Vinkius account to connect Chameleon.io 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 Chameleon.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Chameleon.io Data with Vercel AI SDK

Building user-facing onboarding dashboards requires live data, not loading spinners. You wire up `list_experiences` and `list_microsurvey_responses` through the Vercel AI SDK to pull tour completion rates and user feedback. The text streams directly into your Next.js components as the AI fetches it from the MCP Server. Edge compatibility means these calls run close to your users. When an end user asks about their onboarding progress, your prompt triggers `get_experience_details` instantly. The result renders in the UI before the underlying HTTP request even finishes closing.

Trigger Live Onboarding Events

Static product tours annoy users who already know what they are doing. Hooking up `track_user_event` lets your AI client fire specific milestones based on natural language conversations. If someone asks how to export a report, your agent answers the question and simultaneously logs the custom event in Chameleon. Managing user identity happens in the background. You call `identify_chameleon_user` to sync profile properties like subscription tier or role. That data updates instantly, ensuring the right microsurveys trigger during their current session.

Analyze User Segments on the Fly

Fetching target audiences usually means jumping between tabs. Your agent can execute `list_user_segments` to grab the raw list of configured cohorts. It then cross-references those segments against active sessions to see who qualifies for a new feature launch. Cleanup operations work just as fast. Passing `delete_chameleon_user` handles GDPR requests directly from your admin dashboard. You just call `mcpClient.close()` when the transaction finishes to keep your connection pool clean.

Setup guide

Set up Chameleon.io 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 Chameleon.io 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 Chameleon.io 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 Chameleon. 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 Chameleon.io 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 Chameleon.io MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package via npm. You initialize the connection using `createMCPClient` with your Vinkius HTTP URL. Pass the resulting tools directly into `generateText` or `streamText`.

Yes, the AI streams the output of `list_microsurvey_responses` as it generates the summary. Your React or Vue frontend displays the feedback text chunk by chunk. Users see the analysis immediately.

The HTTP transport layer works perfectly on the edge. You just need to ensure your Vinkius endpoint token is passed securely in the environment variables.

The tool returns an error object that the agent can read. You can configure the prompt to either retry the event tracking or inform the user that the milestone was not recorded.

Every microsurvey response and custom event passes through an ephemeral V8 isolate sandbox. The connection dies the moment your Vercel AI SDK client calls `mcpClient.close()`. Nothing persists on our infrastructure.

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