meta-ads-manager-mcp

meta-ads-manager-mcp

Enables users to create, manage, and monitor Meta (Facebook/Instagram) ad campaigns directly from Claude using natural language.

Category
Visit Server

README

meta-ads-manager-mcp

MCP server for creating and managing Meta (Facebook/Instagram) ad campaigns directly from Claude. Tell Claude what you want. It deploys.

Built by Attainment Labs.


What it does

Add this server to your Claude config. You get 5 tools:

Tool What it does
create_meta_campaign Create a full campaign: campaign, ad set, creatives, and ads
get_campaign_status Check status of a campaign, its ad sets, and ads
pause_campaign Pause a live campaign
activate_campaign Activate a paused campaign
delete_campaign Permanently delete a campaign

All campaigns are created as PAUSED by default. You review before spending.


Install

Option 1: Let Claude set it up for you (easiest)

If you use Claude Code, paste this prompt:

"Set up meta-ads-mcp for me: https://github.com/attainmentlabs/meta-ads-mcp"

Claude will check your environment, walk you through getting your Meta credentials step by step, edit your ~/.mcp.json, and confirm when it's done. No docs to read.


Option 2: uvx (recommended, no install needed)

# No setup required — uvx runs it directly

Add to ~/.mcp.json:

{
  "mcpServers": {
    "meta-ads": {
      "command": "uvx",
      "args": ["meta-ads-manager-mcp"],
      "env": {
        "META_ACCESS_TOKEN": "your-token-here",
        "META_AD_ACCOUNT_ID": "your-account-id",
        "META_PAGE_ID": "your-page-id"
      }
    }
  }
}

Option 2: pip install

pip install meta-ads-manager-mcp

Then in ~/.mcp.json:

{
  "mcpServers": {
    "meta-ads": {
      "command": "meta-ads-manager-mcp",
      "env": {
        "META_ACCESS_TOKEN": "your-token-here",
        "META_AD_ACCOUNT_ID": "your-account-id",
        "META_PAGE_ID": "your-page-id"
      }
    }
  }
}

Credentials

You need three values from Meta. Full step-by-step walkthrough: SETUP.md

Variable Where to find it
META_ACCESS_TOKEN Graph API Explorer — long-lived token with ads_management permission
META_AD_ACCOUNT_ID Business Manager: Ad Accounts — numbers only, no act_ prefix
META_PAGE_ID Facebook Page: About → Page transparency → Page ID

The access token expires after 60 days. See SETUP.md for the exchange flow.


Usage examples

Once the server is connected, just describe what you want:

Create a campaign:

"Create a Meta campaign targeting US fitness enthusiasts aged 25-40. Daily budget $30. Use the image at /Users/me/ads/hero.jpg. Copy: 'Track every rep. Hit every goal.' Headline: 'FitCommit AI'. CTA: Learn More. Link to fitcommit.ai."

Check status:

"What's the status of campaign 120243616427570285?"

Pause:

"Pause campaign 120243616427570285."

Activate:

"Go live with campaign 120243616427570285."

Delete:

"Delete campaign 120243616427570285."


dry_run mode

create_meta_campaign defaults to dry_run=True. This simulates all API calls and returns fake IDs without making any requests or spending money. Set dry_run=False when you're ready to deploy.


YAML workflow

Prefer writing campaigns as config files? Use meta-ads-cli — the companion CLI tool.


Requirements

  • Python 3.9+
  • uv for the uvx install path
  • A Meta Business Manager account with an ad account and Facebook Page

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured