Facebook Ads MCP Server

Facebook Ads MCP Server

By Tisik79 GitHub

MCP server pro zadávání a vyhodnocování reklamních kampaní na Facebooku pomocí Claude AI

Overview

What is MCP-Facebook?

MCP-Facebook is a server designed for managing and evaluating advertising campaigns on Facebook using Claude AI. It provides an interface for communication with the Facebook Marketing API through the Model Context Protocol (MCP).

How to use MCP-Facebook?

To use MCP-Facebook, clone the repository from GitHub, install the dependencies, configure your Facebook app credentials in a .env file, compile the TypeScript, and start the server.

Key features of MCP-Facebook?

  • Campaign Management: Create, retrieve, update, and delete advertising campaigns.
  • Analytics and Reporting: Get performance insights, compare campaigns, and analyze audience demographics.
  • Audience Management: Create custom and lookalike audiences, manage user lists.
  • AI Assistance: Utilize prompt templates for Claude AI, analyze campaign performance, and receive optimization recommendations.

Use cases of MCP-Facebook?

  1. Managing multiple Facebook ad campaigns efficiently.
  2. Analyzing campaign performance to optimize ad spend.
  3. Creating targeted audiences for better ad reach.

FAQ from MCP-Facebook?

  • What are the requirements to use MCP-Facebook?

You need Node.js (version 18 or higher), a Facebook Business Manager account, a Facebook App with access to the Marketing API, and a valid access token.

  • Is there a license for MCP-Facebook?

Yes, it is distributed under the MIT license.

  • How secure is MCP-Facebook?

It requires secure handling of access tokens and recommends using environment variables for sensitive data.

Content

Facebook Ads MCP Server

This project provides a Model Context Protocol (MCP) server designed to interact with the Facebook Marketing API, allowing AI assistants like Claude to manage and analyze Facebook ad campaigns, ad sets, audiences, and more.

Features

  • Campaign Management: Create, read, update, delete campaigns.
  • Audience Management: Create custom and lookalike audiences, list audiences.
  • Ad Set Management: Create ad sets (basic implementation).
  • Analytics: Get campaign insights.
  • AI Assistance: Generate prompts for campaign creation based on templates.

Prerequisites

  • Node.js (v18 or later recommended)
  • npm (comes with Node.js)
  • A Facebook App with access to the Marketing API
  • A Facebook Ad Account ID
  • An Access Token with ads_management and ads_read permissions

Installation

  1. Clone the repository: 
    git clone https://github.com/Tisik79/MCP-Facebook.git
cd MCP-Facebook
  2. Install dependencies: 
    npm install
  3. Configure Environment Variables: Create a .env file in the project root and add your Facebook App credentials: 
    FACEBOOK_APP_ID=YOUR_APP_ID
FACEBOOK_APP_SECRET=YOUR_APP_SECRET
FACEBOOK_ACCESS_TOKEN=YOUR_ACCESS_TOKEN 
FACEBOOK_ACCOUNT_ID=act_YOUR_ACCOUNT_ID
    Replace placeholders with your actual values. Ensure the Access Token has the ads_management permission.

Usage

  1. Build the server:

    npm run build

    This compiles the TypeScript code to JavaScript in the dist folder.

  2. Run the server:

    npm start

    The server will start and listen for MCP connections via stdio.

  3. Connect with an MCP Client (e.g., Claude Desktop): Follow the instructions in CLAUDE_DESKTOP_GUIDE.md to configure your MCP client to connect to this server using the npm start command or by directly running node dist/index.js.

Available Tools (via MCP)

  • create_campaign: Creates a new ad campaign.
  • get_campaigns: Lists existing campaigns.
  • get_campaign_details: Gets details for a specific campaign.
  • update_campaign: Updates an existing campaign.
  • delete_campaign: Deletes a campaign.
  • create_custom_audience: Creates a custom, website, or engagement audience.
  • get_audiences: Lists available custom audiences.
  • create_lookalike_audience: Creates a lookalike audience.
  • create_ad_set: Creates a new ad set.
  • get_campaign_insights: Retrieves performance insights for a campaign.
  • generate_campaign_prompt: Generates a prompt for campaign creation using a template.

Refer to the server's tool descriptions in your MCP client for detailed parameter information.

Contributing

Contributions are welcome! Please feel free to submit pull requests or open issues.

License

This project is licensed under the MIT License.

No tools information available.
No content found.