Facebook Ads Library

Facebook Ads Library MCP Server

What is the project about?

This project is a Model Context Protocol (MCP) server specifically designed for the Facebook Ads Library. It allows users to search Facebook's public ad library to analyze advertising strategies of companies and brands.

How to use the project?

To use this project, you need Python 3.12+, Anthropic Claude Desktop app (or Cursor), Pip, and an access token from Scrape Creators. The installation involves cloning the repository, obtaining an API token, and connecting to the MCP server by configuring Claude Desktop or Cursor with the provided JSON. Alternatively, you can use Smithery for automatic installation.

Key features of the project

• Search Functionality: Search Facebook's public ads library for any company or brand.
• Ad Analysis: Analyze ad images and text, and retrieve video links.
• Strategy Comparison: Compare advertising strategies between different companies.
• Insight Generation: Gain insights into effective campaign strategies.
• MCP Tools: Provides get_meta_platform_id to return platform IDs and get_meta_ads to retrieve ads for a specific page.

Use cases of the project

• Competitive Analysis: Understand what competitors are running in their ad campaigns.
• Marketing Research: Conduct deep research into messaging, creative testing, and comparisons.
• Trend Identification: Identify what types of ads and strategies are currently working.
• Content Inspiration: Get inspiration for ad creatives and messaging.

FAQ from the project

• How many ads is 'AnthropicAI' running? What’s their split across video and image?
• What messaging is 'AnthropicAI' running right now in their ads?
• Do a deep comparison to the messaging between 'AnthropicAI', 'Perplexity AI' and 'OpenAI'. Give it a nice forwardable summary.
• Is there a no-code version available? Yes, a no-code version is available via a provided Tally.so link.
• Where can I get updates on this and other projects? You can enter your email on a provided Tally.so link or join their Twitter community.
• How do I troubleshoot Claude Desktop integration issues? Refer to the MCP documentation for helpful tips on checking logs and resolving common issues.

Facebook Ads Library MCP Server

This is a Model Context Protocol (MCP) server for the Facebook Ads Library.

With this you can search Facebook's public ads library for any company or brand, see what they're currently running and analyze their advertising. You can analyse ad images/text, get video links, compare companies' strategies, and get insights into what's working in their campaigns.

Here's an example of what you can do when it's connected to Claude.

https://github.com/user-attachments/assets/a47aa689-e89d-4d4b-9df7-6eb3a81937ee

To get updates on this and other projects we work on enter your email here

PS: Join our Twitter community for all things MCP

---

Example Prompts

How many ads is 'AnthropicAI' running? What’s their split across video and image?

What messaging is 'AnthropicAI' running right now in their ads?

Do a deep comparison to the messaging between 'AnthropicAI', 'Perplexity AI' and 'OpenAI'. Give it a nice forwardable summary.

Don't want to deal with code? Try our no-code version

---

Installation

Prerequisites

• Python 3.12+
• Anthropic Claude Desktop app (or Cursor)
• Pip (Python package manager), install with python -m pip install
• An access token for Scrape Creators

Steps

1. Clone this repository

   git clone https://github.com/trypeggy/facebook-ads-library-mcp.git
   cd facebook-ads-library-mcp
   

2. Obtain an API token from Scrape Creators

   Sign up here

3. Connect to the MCP server

   Copy the below json with the appropriate {{PATH}} values and {{API KEY}}:

   {
     "mcpServers": {
       "fb_ad_library": {
         "command": "python",
         "args": [
           "{{PATH_TO_SRC}}/fb_ad_library_mcp/src/mcp_server.py",
           "--scrapecreators-api-key",
           "{{YOUR_SCRAPECREATORS_API_KEY}}"
         ]
       }
     }
   }
   

   For Claude Desktop:

   Save this as claude_desktop_config.json in your Claude Desktop configuration directory at:

   ~/Library/Application Support/Claude/claude_desktop_config.json
   

   For Cursor:

   Save this as mcp.json in your Cursor configuration directory at:

   ~/.cursor/mcp.json
   

   For Smithery:

   To install Facebook Ads Library for Claude Desktop automatically via Smithery:

   npx -y @smithery/cli install @trypeggy/facebook-ads-library-mcp --client claude
   

4. Restart Claude Desktop / Cursor

   Open Claude Desktop and you should now see the Facebook Ads Library as an available integration.

   Or restart Cursor.

---

Technical Details

1. Claude sends requests to the Python MCP server
2. The MCP server queries the ScrapeCreator API through tools
3. Data flows back through the chain to Claude

Available MCP Tools

This MCP server provides tools for interacting with Facebook Ads library objects:

Tool Name	Description
get_meta_platform_id	Returns platform ID given one or many brand names
get_meta_ads	Retrieves ads for a specific page (platform ID)

---

Troubleshooting

For additional Claude Desktop integration troubleshooting, see the MCP documentation. The documentation includes helpful tips for checking logs and resolving common issues.

---

Feedback

Your feedback will be massively appreciated. Please tell us which features on that list you like to see next or request entirely new ones.

---

License

This project is licensed under the MIT License.