How do I get my Meta Ads API credentials?

1. Go to **developers.facebook.com** and log in. 2. Click **My Apps** → **Create App**. 3. Select **Business** as the app type. 4. Fill in the app name and connect it to your Business Manager. 5. Add the **Marketing API** product to your app. 6. Go to **Settings → Basic** and copy your **App ID** and **App Secret**. 7. Generate a **System User Access Token** in Business Manager (Business Settings → System Users → Generate Token). 8. Paste all values below. 💡 For production use, submit your app

Can I manage both Facebook and Instagram ads?

Yes. Meta Ads Manager unifies Facebook and Instagram advertising. Your AI agent manages campaigns across both platforms through the same API — including placements in Feed, Stories, Reels, and Messenger.

Can I create lookalike audiences?

Yes. Your AI agent can create lookalike audiences from customer lists, website visitors, or app users — with configurable similarity percentages (1% being most similar, 10% broadest reach).

What conversion metrics can I track?

Track purchases, add-to-cart, initiate checkout, lead submissions, app installs, registrations, page views, and custom conversion events — with attribution windows of 1-day click, 7-day click, and 1-day view.

Meta Ads MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Meta Ads
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Meta Ads through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Meta Ads "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Meta Ads?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Meta Ads MCP Server

Connect Meta Ads to your AI agent and manage Facebook and Instagram advertising conversationally.

Pydantic AI validates every Meta Ads tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Campaign Management — List, create, update, and pause campaigns, ad sets, and ads across Facebook and Instagram.
Performance Analytics — Pull impressions, reach, clicks, CTR, CPC, CPM, conversions, ROAS, and frequency metrics.
Audience Management — Create custom audiences, lookalikes, and saved audiences with demographic and interest targeting.
Creative Insights — Compare ad creative performance, view thumbnail engagement, and identify winning variants.

The Meta Ads MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Meta Ads to Pydantic AI via MCP

Follow these steps to integrate the Meta Ads MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Meta Ads with type-safe schemas

Why Use Pydantic AI with the Meta Ads MCP Server

Pydantic AI provides unique advantages when paired with Meta Ads through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Meta Ads integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Meta Ads connection logic from agent behavior for testable, maintainable code

Meta Ads + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Meta Ads MCP Server delivers measurable value.

Type-safe data pipelines: query Meta Ads with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Meta Ads tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Meta Ads and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Meta Ads responses and write comprehensive agent tests

Meta Ads MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Meta Ads to Pydantic AI via MCP:

activate_campaign

Activate a paused campaign

get_account_info

Get ad account details

get_account_insights

Get account-level performance

get_campaign_insights

Get campaign performance metrics

list_ad_sets

List ad sets in a campaign

list_ads

List ads in an ad set

list_audiences

List custom audiences

list_campaigns

List all Meta ad campaigns

list_creatives

List ad creatives

pause_campaign

Can be reactivated later. Pause a campaign

Example Prompts for Meta Ads in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Meta Ads immediately.

"What's my Meta ad spend and ROAS this month?"

"Which ad creatives are performing best?"

"Create a lookalike audience from my top 1000 customers."

Troubleshooting Meta Ads MCP Server with Pydantic AI

Common issues when connecting Meta Ads to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Meta Ads + Pydantic AI FAQ

Common questions about integrating Meta Ads MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Meta Ads MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.