How to Use the Adjust MCP in Vercel AI SDK

Q: How do I feed Adjust tracker configurations into Vercel AI SDK using MCP?

You initialize the client using createMCPClient to connect to our MCP Server. Call mcpClient.tools() and pass them into streamText to let your agent query getappsettings and render active trackers.

Q: Can I stream live Adjust KPI reports to a Next.js UI using Vercel AI SDK?

Yes, the SDK handles streaming naturally. The getkpireport tool outputs structured JSON that the Vercel AI SDK streams directly to your frontend components, eliminating loading screens by rendering live install and event metrics as they arrive.

Q: How does the Vercel AI SDK handle Adjust device inspection?

Your agent calls inspectdevice with a device ID, and the Vercel AI SDK processes the payload within your edge runtime. The returned attribution details stream straight to the user's chat window.

Q: Do I need to manually close the connection after fetching marketing data?

Yes, always call mcpClient.close() once your stream finishes. This prevents connection leaks in your serverless or edge environments when calling the Adjust tools.

Feed live Adjust mobile attribution data directly into 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 Adjust MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live KPI reports to Vercel AI SDK frontends

The `get_kpi_report` tool pulls aggregated marketing performance metrics directly into your Vercel AI SDK stream via the MCP Server. Your Next.js frontend renders actual install numbers and event counts as they arrive from the Adjust API, skipping the usual loading spinners entirely.

Inspect device attribution with Vercel AI SDK tools

Querying the `inspect_device` tool checks the exact attribution status of a mobile device using its ID. Your edge-rendered Vercel AI SDK app calls this endpoint to instantly show which ad campaign brought in a specific user.

Fetch Adjust app settings inside Edge Functions

Running the `get_app_settings` tool retrieves your current Adjust configuration directly within Vercel AI SDK Edge Functions. This setup lets your client inspect active trackers and SDK settings without introducing database overhead.

Setup guide

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

You initialize the client using `createMCPClient` to connect to our MCP Server. Call `mcpClient.tools()` and pass them into `streamText` to let your agent query `get_app_settings` and render active trackers.

Yes, the SDK handles streaming naturally. The `get_kpi_report` tool outputs structured JSON that the Vercel AI SDK streams directly to your frontend components, eliminating loading screens by rendering live install and event metrics as they arrive.

Your agent calls `inspect_device` with a device ID, and the Vercel AI SDK processes the payload within your edge runtime. The returned attribution details stream straight to the user's chat window.

Yes, always call `mcpClient.close()` once your stream finishes. This prevents connection leaks in your serverless or edge environments when calling the Adjust tools.

We route all device IDs and install metrics through an ephemeral, zero-trust V8 sandbox on our MCP platform. No attribution data is stored on our servers, keeping your mobile marketing logs private.

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