How to Use the Measured MCP in Vercel AI SDK

Q: How do I stream Measured marketing reports in Vercel AI SDK?

Call the listreports tool within streamText to fetch available performance reports. The Vercel AI SDK handles the stream, letting your AI client display available marketing documents to the user instantly.

Q: Can Vercel AI SDK fetch Measured campaign incrementality scores on the Edge?

Yes, this MCP Server works in Edge environments. Use getincrementalityscores inside your edge route to get immediate performance lift data without cold-start delays.

Q: How does the Measured integration handle live channel updates in Vercel AI SDK?

Your agent calls listchannels to get active platforms. The Vercel AI SDK streams these channels directly into your React state, rendering the list as the model identifies them.

Q: What is the best way to handle tool calling with getperformancebychannel?

Pass the tool definition to generateText or streamText using the MCP client. The model automatically extracts the channel parameter, runs getperformancebychannel, and outputs the results.

Q: How does this setup protect my sensitive ROAS and campaign spend data?

All marketing performance data processed by getperformancesummary stays inside your V8 sandbox. Vinkius handles the credentials securely, ensuring your raw revenue and spend metrics never leak to public LLM training sets.

Pipe real-time marketing incrementality scores and campaign ROAS directly into your React components with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Measured MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Incrementality Feeds in Vercel AI SDK

This Vercel AI SDK setup connects your React frontend directly to your marketing performance data using the `get_incrementality_scores` tool over an MCP connection. Your AI client pulls raw incrementality data and streams it straight to the user's screen, eliminating loading spinners while calculating lift. By calling `list_channels` alongside your UI components, you render active marketing sources instantly. Users watch the AI compare Facebook and Google Ads performance live, updating the interface as fresh metrics arrive.

Instant Performance Summaries for Edge Runtimes

This Measured MCP Server allows Edge-compatible Next.js routes to fetch high-level marketing data using `get_performance_summary`. Your AI client processes these summaries on the fly, feeding raw numbers to streaming text components without hitting cold starts. You can chain this tool with `list_reports` to let users request specific PDF exports right inside the chat window. The Vercel AI SDK handles the async rendering, keeping your edge functions fast and responsive.

Interactive Campaign Deep-Dives

Run the `get_campaign_performance` tool inside your Vercel AI SDK stream to let users inspect individual marketing campaigns. The agent updates specific UI widgets in real-time as it parses target conversion metrics and spend data. If the numbers don't look right, the agent invokes `get_insights` to explain sudden ROAS drops. The resulting analysis streams word-by-word, keeping your marketing dashboard interactive and fast.

Setup guide

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

Call the `list_reports` tool within `streamText` to fetch available performance reports. The Vercel AI SDK handles the stream, letting your AI client display available marketing documents to the user instantly.

Yes, this MCP Server works in Edge environments. Use `get_incrementality_scores` inside your edge route to get immediate performance lift data without cold-start delays.

Your agent calls `list_channels` to get active platforms. The Vercel AI SDK streams these channels directly into your React state, rendering the list as the model identifies them.

Pass the tool definition to `generateText` or `streamText` using the MCP client. The model automatically extracts the channel parameter, runs `get_performance_by_channel`, and outputs the results.

All marketing performance data processed by `get_performance_summary` stays inside your V8 sandbox. Vinkius handles the credentials securely, ensuring your raw revenue and spend metrics never leak to public LLM training sets.

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