mcp-registry/meta-ads-mcp

    ==================
      
       /// MCP ///
      /// MET ///
        
    ==================
        
    [server:online]
    [protocol:ready]

meta-ads-mcp

by pipeboard-co

Model Context Protocol (MCP) server that lets AI agents query and manage Facebook / Instagram (Meta) advertising accounts, campaigns, ad-sets, creatives and insights via Meta’s Marketing API.

187
48
Specialized
GitHub

Installation

1. Prerequisites
• Python 3.10 or later installed and available on PATH.
• A Meta (Facebook) App with Marketing API permissions and a System-User Access-Token that has `ads_management` scope.
• (Optional) Docker & Docker-Compose if you prefer running the server in a container.
2. Clone the repository
git clone https://github.com/pipeboard-co/meta-ads-mcp.git cd meta-ads-mcp
3. Create and activate a virtual environment
python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate
4. Install package requirements
pip install -r requirements.txt
5. Configure environment variables (create a `.env` file or export in shell)
META_APP_ID=<your-app-id> META_APP_SECRET=<your-app-secret> META_ACCESS_TOKEN=<system-user-token-with-ads_management> MCP_PORT=8000 # port the server will listen on
6. Run database migrations (if the project ships with Alembic or Django)
# example using Alembic alembic upgrade head
(Skip if the project is purely stateless.)
7. Start the MCP server
uvicorn meta_ads_mcp.app:app --host 0.0.0.0 --port ${MCP_PORT:-8000}
8. (Optional) Docker way
docker compose up -d
Once the service is up, visit http://localhost:8000/docs for the auto-generated OpenAPI UI.

Documentation

License: Apache License 2.0
Updated 7/30/2025