How to Use the Meta Ads MCP in Mastra AI

Q: How do I build a self-healing Meta Ads workflow in Mastra AI?

Map getcampaigninsights inside a Mastra AI workflow step to monitor Facebook campaign performance, and configure retries for any Meta API hiccups. The Mastra AI workflow automatically triggers fallback logic if a Meta Ads API request fails. This setup keeps your Facebook budget monitoring accurate 24/7 inside the Mastra AI agent.

Q: Can Mastra AI automatically pause underperforming Meta Ads?

Yes, design a Mastra AI workflow that queries getcampaigninsights and triggers pausecampaign if your Facebook cost-per-click spikes. The Mastra AI system evaluates the Meta Ads rules you define inside your agent. You can halt bleeding Facebook ad sets within seconds of a performance drop using Mastra AI.

Q: How do I register the Meta Ads MCP Server with Mastra AI?

Instantiate the MCPClient in your Mastra AI project and spread the Meta Ads tools returned by listTools into your agent configuration. Mastra AI automatically registers every Meta Ads endpoint as a callable tool. Your Mastra AI agent can immediately start querying Facebook metrics using this MCP connection.

Automate your Meta Ads optimization using Mastra AI workflows that pause bad ads and retry failed API calls.

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 Mastra AI

Create your Vinkius account to connect Meta Ads to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Campaign Optimization Workflows

The `pause_campaign` tool allows your Mastra AI agent to halt failing Facebook ad sets automatically. By nesting this tool inside a Mastra workflow, you can set strict rules to stop ads that cross a specific cost-per-click threshold. If Meta's API rate limits hit during optimization, the Mastra AI workflow automatically retries the call with exponential backoff. This ensures you never waste money on a dead Instagram campaign just because an API request failed.

Budget Reallocation via MCP Server

The `get_account_insights` tool monitors your daily spend limits across all active Facebook campaigns. Mastra AI uses this performance data to decide where to shift budget dynamically. Your agent can trigger `activate_campaign` to scale winning Meta ad sets when performance metrics look strong. All of this runs in a self-healing Mastra AI workflow that notifies your team if anything goes wrong.

Human-in-the-Loop Audience Syncing

The `list_audiences` tool pulls your current Meta custom audiences to check for targeting overlap. Mastra AI lets you build an approval step directly into this MCP workflow before modifying any ad group targeting. When the Mastra AI agent wants to update Meta targeting, it pauses and waits for your thumbs-up in Slack. Once approved, the workflow resumes and updates your Facebook parameters using `list_ad_sets`.

Setup guide

Set up Meta Ads MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Meta Ads tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "meta-ads-mcp-client",
  servers: {
    "meta-ads-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Meta Ads Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Meta Ads tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Meta Ads transactions"
);
console.log(result.text);

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 Mastra AI

Map `get_campaign_insights` inside a Mastra AI workflow step to monitor Facebook campaign performance, and configure retries for any Meta API hiccups. The Mastra AI workflow automatically triggers fallback logic if a Meta Ads API request fails. This setup keeps your Facebook budget monitoring accurate 24/7 inside the Mastra AI agent.

Yes, design a Mastra AI workflow that queries `get_campaign_insights` and triggers `pause_campaign` if your Facebook cost-per-click spikes. The Mastra AI system evaluates the Meta Ads rules you define inside your agent. You can halt bleeding Facebook ad sets within seconds of a performance drop using Mastra AI.

Instantiate the `MCPClient` in your Mastra AI project and spread the Meta Ads tools returned by `listTools` into your agent configuration. Mastra AI automatically registers every Meta Ads endpoint as a callable tool. Your Mastra AI agent can immediately start querying Facebook metrics using this MCP connection.

Mastra AI features built-in exponential backoff, retrying failed calls to `list_ads` until Meta successfully returns your active ad sets. This prevents Meta API rate limiting errors from breaking your Mastra AI automation. Your Mastra AI workflow handles transient Facebook API errors without crashing.

Your tokens never touch disk, as Vinkius runs the MCP Server in an ephemeral sandbox to fetch `get_account_info` securely for Mastra AI. The session discards all Facebook ad account keys immediately after Mastra AI finishes querying campaign metrics. We adhere to strict zero-trust standards to protect your Meta Ads marketing data inside Mastra AI.

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