Skip to content

Facebook Ads Library MCP

MCP Server for Facebook ADs Library - Get instant answers from FB's ad library

Install

$git clone https://github.com/proxy-intell/facebook-ads-library-mcp

Install command taken from the project's README or registry entry. Always review code before running it.

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 analyze ad images/text, analyze video ads with comprehensive insights, 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


Hosted Version (Recommended)

The easiest way to use the Facebook Ads Library MCP is the hosted version from Proxy (useproxy.dev). No API keys, no Gemini key, no Python, no server to run — just connect and start querying.

  • ⚡ Zero setup — nothing to install, configure, or maintain
  • 🔑 No API keys — skip the ScrapeCreators and Gemini keys entirely
  • 🔌 Works everywhere — ChatGPT, Claude, Cursor, Manus, and anywhere else that supports MCP
  • 🚀 Always up to date — new tools and fixes ship automatically

👉 Get started for free at useproxy.dev →

Prefer to run it yourself? The full self-host setup is documented below.

Hosted vs. Self-Host

Hosted — Proxy (useproxy.dev) Self-Host
Setup time None — connect and go Python env + config
API keys required None ScrapeCreators + Gemini
Infrastructure Fully managed You run and maintain it
Updates Automatic Manual git pull
Works in ChatGPT, Claude, Cursor, Manus ✅ ✅
Best for Most users who just want the data Developers who want to customize the code

For most people, the hosted version is the fastest path. Choose self-host if you specifically want to modify or extend the server yourself.


Example Prompts

Single Brand Analysis

How many ads is 'AnthropicAI' running? What's their split across video and image?
What messaging is 'AnthropicAI' running right now in their ads?
Analyze the video ads from 'Nike' and extract their visual storytelling strategy, pacing, and brand messaging techniques.

Batch Analysis (New!)

Compare the current advertising strategies across Nike, Adidas, and Under Armour. Show me their ad volumes, messaging themes, and creative approaches.
Do a deep comparison to the messaging between 'AnthropicAI', 'Perplexity AI' and 'OpenAI'. Give it a nice forwardable summary.
Analyze the holiday campaign strategies for Coca-Cola, Pepsi, Dr Pepper, and Sprite. What themes are they using?
Get the current ads for all major streaming services: Netflix, Disney+, Hulu, HBO Max, Amazon Prime Video, and Apple TV+. Compare their positioning strategies.

Installation

Prerequisites

  • Python 3.12+
  • Anthropic Claude Desktop app (or Cursor)
  • Pip (Python package manager), install with python -m pip install
  • An API key for an ads data provider, set as SCRAPECREATORS_API_KEY (see configuration below)
  • A Google Gemini API key for video analysis (optional, only needed for video ads)

Similar plugs

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

Explore related