How to Use the Meta Ads MCP in Vercel AI SDK

Q: How do I stream live Meta Ads metrics using Vercel AI SDK?

Call getcampaigninsights inside your streamText block to stream raw Facebook campaign metrics directly to your Vercel AI SDK UI components. This streaming method removes any intermediate server lag between Meta's servers and your Vercel AI SDK application. Your users will see active Facebook ad spend and conversions update in real-time inside your Next.js UI via Vercel AI SDK.

Q: Can I build a custom dashboard for Meta Ads with Vercel AI SDK?

Yes, instantiate createMCPClient in Next.js and pass listcampaigns to let Vercel AI SDK stream your active ad accounts live. The Vercel AI SDK client manages the HTTP connection to your Facebook ad account automatically. You can then map the Meta campaign list straight to React components using Vercel AI SDK helper functions.

Q: How does Vercel AI SDK handle Meta Ads OAuth?

Pass the user's Facebook token via the authProvider in your Vercel AI SDK client setup to secure calls to getaccountinfo. This guarantees that your Meta Ads API tokens are encrypted during transit within the Vercel AI SDK pipeline. Your Next.js application code never exposes raw Meta Ads credentials to the frontend.

Q: Does this Meta Ads MCP Server setup support Vercel AI SDK on Next.js Edge Functions?

Yes, you can deploy Vercel AI SDK edge routes that query listadsets from the Meta Ads MCP Server without cold-start delays. Edge compatibility ensures your Vercel AI SDK Facebook reporting tools load instantly. This edge setup delivers your Meta Ads metrics globally with zero Vercel AI SDK performance degradation.

Watch your Meta Ads metrics stream live into your Next.js UI using the Vercel AI SDK without waiting for slow API responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Meta Ads MCP to Vercel AI SDK

Create your Vinkius account to connect Meta Ads 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 Meta Ads with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Campaign Control in Vercel AI SDK

The `pause_campaign` tool stops bleeding ad spend on Facebook instantly inside your Vercel AI SDK application. When your user clicks pause, this MCP Server executes the action on Meta's servers, streaming the updated status directly to your Vercel AI SDK frontend in milliseconds. Next.js components render the Meta campaign status change without a page refresh. You can also trigger `activate_campaign` via Vercel AI SDK to restart top-performing Instagram ads during peak traffic hours.

Real-Time Performance Dashboard

The `get_campaign_insights` tool fetches real-time conversion rates and spend metrics from your Facebook ad account directly into your Vercel AI SDK app. Your Vercel AI SDK application streams these raw numbers directly into charts as they arrive from the Meta API. Users get instant visibility into their Meta Ads return on ad spend through the streaming Vercel AI SDK interface. Running this on Next.js Edge Functions ensures low latency, meaning your Vercel AI SDK dashboard loads Meta Ads performance data in under 100 milliseconds.

Visual Asset Auditing

The `list_creatives` tool pulls active Meta ad images and copy directly into your Vercel AI SDK client. Your Vercel AI SDK app displays these visual Meta Ads assets side-by-side with performance metrics using this MCP connection. This setup lets Next.js users inspect what their Facebook audience actually sees in real-time using Vercel AI SDK. Combine it with `list_ads` to let Vercel AI SDK pinpoint which specific creative variations drive the lowest cost per acquisition.

Setup guide

Set up Meta Ads 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 Meta Ads 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 Meta Ads 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 Meta Ads. 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 Meta Ads 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 Meta Ads MCP in Vercel AI SDK

Call `get_campaign_insights` inside your streamText block to stream raw Facebook campaign metrics directly to your Vercel AI SDK UI components. This streaming method removes any intermediate server lag between Meta's servers and your Vercel AI SDK application. Your users will see active Facebook ad spend and conversions update in real-time inside your Next.js UI via Vercel AI SDK.

Yes, instantiate `createMCPClient` in Next.js and pass `list_campaigns` to let Vercel AI SDK stream your active ad accounts live. The Vercel AI SDK client manages the HTTP connection to your Facebook ad account automatically. You can then map the Meta campaign list straight to React components using Vercel AI SDK helper functions.

Pass the user's Facebook token via the `authProvider` in your Vercel AI SDK client setup to secure calls to `get_account_info`. This guarantees that your Meta Ads API tokens are encrypted during transit within the Vercel AI SDK pipeline. Your Next.js application code never exposes raw Meta Ads credentials to the frontend.

Yes, you can deploy Vercel AI SDK edge routes that query `list_ad_sets` from the Meta Ads MCP Server without cold-start delays. Edge compatibility ensures your Vercel AI SDK Facebook reporting tools load instantly. This edge setup delivers your Meta Ads metrics globally with zero Vercel AI SDK performance degradation.

Yes, Vercel AI SDK only processes your custom audiences in memory, routing calls to `list_audiences` through the secure Vinkius sandbox. We never write your Facebook custom audiences or campaign metrics to persistent storage during Vercel AI SDK operations. Your proprietary Meta Ads marketing data remains completely private inside the Vercel AI SDK sandbox.

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