How to Use the Mode Analytics MCP in Vercel AI SDK

Q: How do I stream Mode Analytics report lists using the Vercel AI SDK?

Use the listmodereports tool inside your streamText call. The Vercel AI SDK handles the tool execution on the edge and streams the resulting report metadata straight to your React UI.

Q: Can the Vercel AI SDK trigger a new Mode Analytics report run?

Yes. Your agent can call runmodereport to start the execution. It then uses getmodereportrun to track the progress and update the frontend.

Q: What is the best way to clean up the Vercel AI SDK client connections?

Always call mcpClient.close() once your text generation or streaming session finishes. This prevents memory leaks and keeps your edge environment clean.

Stream Mode Analytics report runs and SQL query results directly into your Next.js UI using 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 Mode Analytics MCP to Vercel AI SDK

Create your Vinkius account to connect Mode Analytics 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 Mode Analytics with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream raw data directly to React components

Your users don't want to wait for a full page reload or stare at a blank loading spinner while a heavy SQL query executes. This MCP integration lets your Vercel AI SDK client fetch active report definitions using `list_mode_queries` and render the incoming data structure as it arrives. You get raw JSON streamed straight into your custom UI components on the edge. Developers can build direct data-exploration interfaces where the end user asks a question, and the agent pulls the exact SQL schema from `list_mode_definitions`. No intermediate servers or heavy database drivers are needed in your Next.js API routes.

Trigger live runs via this Mode Analytics MCP Server

Long-running data jobs shouldn't block your edge functions. Fire off a fresh run of any workspace report with `run_mode_report` and let your Vercel AI SDK agent poll the execution status in the background. The agent uses `get_mode_report_run` to check the progress and streams status updates directly to the client's screen. This setup prevents your Vercel edge functions from timing out on heavy analytics tasks. By offloading the execution to Mode and streaming the status updates, your app remains responsive and fast.

Explore spaces and reports interactively

Give your users a conversational way to find the data they need. Your agent can list every available space using `list_mode_spaces` and drill down into specific reports with `list_mode_reports`. Once the right report is located, the agent pulls its metadata via `get_mode_report`. This keeps your users in their flow without forcing them to manually search through the Mode web interface.

Setup guide

Set up Mode Analytics 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 Mode Analytics 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 Mode Analytics 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 Mode Analytics. 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 Mode Analytics 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 Mode Analytics MCP in Vercel AI SDK

Use the `list_mode_reports` tool inside your `streamText` call. The Vercel AI SDK handles the tool execution on the edge and streams the resulting report metadata straight to your React UI.

Yes. Your agent can call `run_mode_report` to start the execution. It then uses `get_mode_report_run` to track the progress and update the frontend.

It prevents them by using asynchronous execution. Instead of holding the connection open, the server triggers the run and lets the SDK poll the status asynchronously.

Always call `mcpClient.close()` once your text generation or streaming session finishes. This prevents memory leaks and keeps your edge environment clean.

All API tokens and SQL queries are processed within a secure, ephemeral V8 isolate sandbox. Your database credentials and raw Mode report outputs never persist on our 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