Facebook Ads Library MCP Server
Public advertising data search for analyzing competitor strategies and campaigns.
Data last scanned today · Reviewed today
Overview
The Facebook Ads Library MCP Server allows users to query and analyze active advertisement campaigns from any brand directly through their AI assistant. It provides capabilities to retrieve ad volume statistics, review messaging themes, and evaluate creative approaches for both image and video advertisements across multiple companies. The server facilitates both individual brand audits and batch comparative analysis, enabling users to identify industry trends and messaging strategies. While users can self-host the Python-based implementation, the provider recommends a managed version that eliminates the need for external API keys and local environment maintenance.
Our verdict
With a security score of 43/100, this server is currently classified as high-risk. A significant concern is the lack of a read-only mode, as the current implementation grants full write access upon installation. Additionally, as a community-maintained project that has not yet undergone editorial review, users should exercise caution when deploying it in environments where strict access control is required. It is best suited for developers and researchers who prioritize rapid access to ad data over hardened security configurations.
- Supports comparative analysis across multiple brands simultaneously
- Zero direct dependencies simplifies the supply-chain surface
- Provides automated access to public advertising metadata
- MIT license allows for modification and local extension
- No read-only mode limits granular permission controls
- Community-maintained status lacks official vendor backing
- Lacks documented support for OAuth authentication methods
Tools
| Tool | Description | Risk |
|---|---|---|
| get_meta_platform_id | Returns platform ID given one or many brand names | low |
| get_meta_ads | Retrieves ads for specific page(s) (platform ID) | low |
| analyze_ad_image | Analyzes ad images for visual elements, text, colors, and composition | low |
| analyze_ad_video | Analyzes single ad video using Gemini AI for comprehensive insights | low |
| analyze_ad_videos_batch | Analyzes multiple videos in single API call for token efficiency | low |
| get_cache_stats | Gets statistics about cached media (images and videos) and storage usage | low |
| search_cached_media | Searches previously analyzed media by brand, colors, people, or media type | low |
| cleanup_media_cache | Cleans up old cached media files to free disk space | medium |
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf | ||||
| ChatGPT |
Frequently asked questions
›What are the prerequisites for running the self-hosted version of this server?
You need Python 3.12+, the Claude Desktop app or Cursor, and an API key for an ads data provider (SCRAPECREATORS_API_KEY). A Google Gemini API key is also required if you intend to perform video ad analysis.
›Can I use the MCP server without managing my own API keys?
Yes, by using the hosted version provided by Proxy (useproxy.dev). This version requires no API keys, no installation, and no server maintenance.
›What is the difference between the hosted and self-hosted versions?
The hosted version is managed by Proxy and requires no setup or keys, while the self-hosted version requires you to install Python, manage dependencies, and provide your own API keys.
›Is a Gemini API key mandatory for all features?
No, the Google Gemini API key is optional and is only required if you want the server to perform video ad analysis.
›How do I configure API keys for the self-hosted version?
You should add your keys to the .env file generated in the project directory. The server automatically loads these keys from that file.
Badge
Maintain this server? Add the live badge to your README.