How to Use the Contentsquare MCP in Vercel AI SDK

Q: How do I stream Contentsquare metrics using Vercel AI SDK?

You install the @ai-sdk/mcp package and initialize the client with createMCPClient pointing to your Vinkius endpoint. Pass the tools directly to your streamText function so your agent can call getmetrics and render the UX data in real-time.

Q: Can Vercel AI SDK handle Contentsquare raw export jobs?

Yes. The model triggers createexportjob to queue the extraction, then uses getexportjob to track progress. Because it runs on the edge, you must call mcpClient.close() once the export state returns a success code.

Q: How does Vercel AI SDK resolve Contentsquare URL mappings?

The model calls listmappings to discover the routing trees for specific URL paths. It then matches those paths against live session data, outputting clean mapping tables directly to your Next.js frontend.

Q: What is the fastest way to fetch segments?

Have your agent call listsegments. That'll return demographic limits in a clean JSON array, which the model instantly parses and displays inside your streaming UI components.

Feed raw Contentsquare UX metrics and session logs directly into your Vercel AI SDK streaming UI without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Contentsquare MCP to Vercel AI SDK

Create your Vinkius account to connect Contentsquare 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 Contentsquare with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Contentsquare metrics live with Vercel AI SDK

The `get_metrics` tool pulls raw bounce rates and engagement numbers directly into your edge-rendered frontend. Your agent calls this tool to populate UI components on the fly, so users don't have to wait for a full page reload. You set up the connection using `createMCPClient` and pass the tools array directly to `streamText`. This keeps the data pipeline tight, letting the model query `get_page_metrics` and format the raw URL statistical bodies directly into Next.js components.

Analyze segment trends in the UI

The `list_segments` tool feeds demographic JSON arrays straight to your active Vercel AI SDK session. Your agent reads these demographic limits to map user behaviors, matching them against actual site performance metrics without manual querying. By calling `list_zonings` alongside the segment list, the model identifies exactly where click tracking constraints are causing friction. The UI updates instantly as the model processes the interaction arrays, rendering clean visual breakdowns of user friction points.

Manage raw data export pipelines

The `create_export_job` tool starts an automated validation check that routes raw Contentsquare data chunks to your storage. Your Vercel AI SDK app monitors this process by calling `get_export_job` to verify the execution state of the data extraction queue. Once the model confirms the export state, it calls `list_export_jobs` to verify structural log payloads before closing the connection. Remember to call `mcpClient.close()` in your Next.js edge route to prevent memory leaks and keep your serverless functions clean.

Setup guide

Set up Contentsquare 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 Contentsquare 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 Contentsquare 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 Contentsquare. 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 Contentsquare 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 Contentsquare MCP in Vercel AI SDK

You install the `@ai-sdk/mcp` package and initialize the client with `createMCPClient` pointing to your Vinkius endpoint. Pass the tools directly to your `streamText` function so your agent can call `get_metrics` and render the UX data in real-time.

Yes. The model triggers `create_export_job` to queue the extraction, then uses `get_export_job` to track progress. Because it runs on the edge, you must call `mcpClient.close()` once the export state returns a success code.

The model calls `list_mappings` to discover the routing trees for specific URL paths. It then matches those paths against live session data, outputting clean mapping tables directly to your Next.js frontend.

Have your agent call `list_segments`. That'll return demographic limits in a clean JSON array, which the model instantly parses and displays inside your streaming UI components.

This MCP Server runs inside an isolated V8 sandbox on Vinkius, meaning your session arrays and demographic limits never touch external servers. All data transfers use single-token authorization, keeping your raw export payloads locked down and ephemeral.

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