Ad Library MCP
Provides tools for searching and retrieving ad data from Google Ads Transparency Center, including headlines, descriptions, impressions, and regional breakdown.
Provides tools for searching Reels, retrieving creator profiles with viral ratio rankings, and transcribing Reels.
Provides tools for searching and retrieving ad data from the Meta Ad Library, including ad copy, images, videos, targeting, and transcripts.
Provides tools for searching videos, retrieving creator profiles, and pulling comments with keyword filtering.
Provides tools for searching creators and channels, retrieving channel profiles with engagement metrics as percentage of subscribers.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Ad Library MCPsearch ads for Nike"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Ad Library MCP
Self-hosted MCP server for searching competitor ads and content across Meta Ad Library, Google Ads Transparency Center, Instagram, TikTok, and YouTube. All data sources are public — no ad account credentials required.
You bring your own ScrapeCreators API key and deploy to your own Fly.io account.
Prerequisites
ScrapeCreators API key — sign up at scrapecreators.com
Fly.io account — sign up at fly.io (free tier works)
Fly CLI — install with
brew install flyctlor see fly.io/docs/flyctl/installClaude Code — claude.ai/code
Optional: Gemini API key for the analyze-creatives tool (AI-powered image/video analysis). Get one free at aistudio.google.com/apikey.
Deploy (5 minutes)
# 1. Clone and install
git clone https://github.com/superpower-growth/ad-library-mcp.git
cd ad-library-mcp
npm install
# 2. Deploy to Fly.io
fly auth login
fly launch # Creates your app — say yes to defaults
# 3. Set your API keys as secrets
fly secrets set SCRAPECREATORS_API_KEY=your-scrapecreators-key
fly secrets set GEMINI_API_KEY=your-gemini-key # optional
# 4. Deploy
fly deploy
# 5. Verify it's running
curl https://YOUR-APP-NAME.fly.dev/healthfly launch will assign your app a unique name (e.g. my-ad-library-mcp). Use that name in the URL below.
Connect to Claude Code
Once deployed, add it to Claude Code with your app's URL:
claude mcp add ad-library --transport http https://YOUR-APP-NAME.fly.dev/mcpOr add to .mcp.json:
{
"ad-library": {
"type": "http",
"url": "https://YOUR-APP-NAME.fly.dev/mcp"
}
}Replace YOUR-APP-NAME with the name from fly launch.
Local Development
cp .env.example .env
# Edit .env — add your ScrapeCreators API key (required)
npm run dev # Starts on http://localhost:3002Test locally with Claude Code:
claude mcp add ad-library-local --transport http http://localhost:3002/mcpTools
Tool | Platform | What it does |
| Cross-platform | Find a company using 5 parallel strategies: name search, domain lookup, keyword search, website scrape, and active ad count verification. Returns confidence-ranked matches. |
| Meta | Search ads by keyword or company page ID. Configurable limit (1-1000). |
| Meta | Full ad details: copy, carousel cards (per-card content), caption, video URLs, targeting, transcript, Ad Library link. |
| List ads by domain or advertiser ID. Optional full details (headlines, descriptions, impressions, regions). | |
| Full ad details: creative variations, OCR text, impression ranges, regional breakdown, Transparency Center link. | |
| Cross-platform | Batch Gemini AI analysis of images and videos: visual descriptions, text overlay extraction, full verbatim transcripts, messaging themes, hooks. Requires Gemini API key. |
| Search Reels by keyword, ranked by viral ratio (views / followers). BREAKOUT/STRONG/GOOD labels. | |
| Creator profile with top Reels sorted by views and viral ratio. | |
| Transcribe a Reel via ScrapeCreators (Gemini AI fallback). | |
| TikTok | Search videos by keyword or #hashtag, ranked by viral ratio. Auto-detects hashtags. |
| TikTok | Creator profile with top videos ranked by views and viral ratio. |
| TikTok | Video comments sorted by likes. Optional keyword filter for finding audience pain points. |
| YouTube | Search creators in a niche, ranked by median views/subscribers across surfaced videos. Returns subs, top videos, and view/like/comment engagement as % of subscribers. |
| YouTube | Channel profile + top videos with views/likes/comments expressed as % of subscribers. Useful for benchmarking against audience size. |
How resolve-company Works
The most important tool — finds the right brand across platforms using a 2-phase approach that minimizes API credits.
Phase 1 (always runs, ~3 credits):
Strategy | What it does | Cost |
1. Name search | Searches Meta companies + Google advertisers by brand name | 2 credits |
2. Domain lookup | Infers domain from name, searches Google by domain | 1 credit |
4. Website scrape | Fetches homepage, parses for Facebook page link | Free |
Phase 2 (only if Phase 1 result is ambiguous, +1-4 credits):
Strategy | What it does | Cost |
3. Keyword search | Searches Meta ads for the domain in ad content — finds partner/influencer pages | 1 credit |
5. Ad count verify | Checks active ad count on top Meta pages — strongest signal | 1 credit each (up to 3) |
Caching: Results cached for 10 minutes. Second lookup for the same brand is instant (0 credits).
Usage Flow
1. resolve-company query="<brand name>"
-> Confidence-ranked matches with Page IDs, Advertiser IDs, active ad counts
2. meta-search-ads page_id="<page_id>" limit=10
-> Newest ads with copy, format, CTA, carousel card count, and Ad Library links
3. meta-get-ad id="<ad_id>" get_transcript=true
-> Full ad detail: carousel cards with per-card content, caption, video transcript, targeting
4. google-search-ads domain="<domain>" get_ad_details=true
-> Headlines, descriptions, impressions, regions, landing pages, Transparency Center links
5. analyze-creatives creatives=[{url: "<image_or_video_url>", type: "video"}]
-> Batch AI analysis: visual descriptions, full verbatim transcript, messaging themes, hooks
6. ig-search-reels query="<keyword>"
-> Reels ranked by viral ratio (views / followers)
7. tiktok-search-videos query="<keyword>"
-> Videos ranked by viral ratio (views / followers)
8. youtube-search-creators query="<niche>"
-> Creators ranked by median views/subscribersEnvironment Variables
Set as Fly.io secrets (fly secrets set KEY=value) or in .env for local dev.
Variable | Required | Description |
| Yes | API key from scrapecreators.com |
| No | Google AI key for |
| No | Gemini model (default: |
| No | Server port (default: 3002) |
CI/CD (Optional)
The repo includes a GitHub Actions workflow (.github/workflows/fly-deploy.yml) that auto-deploys on push to main. To use it:
Fork the repo
Add your Fly.io API token as a GitHub secret named
FLY_API_TOKENGenerate one with
fly tokens create deploy -x 999999h
Push to
main— it deploys automatically
Data Sources
Meta Ad Library — via ScrapeCreators API. Ad copy, images, video URLs, CTA, impressions, spend, targeting, carousel cards, transcripts.
Google Ads Transparency Center — via ScrapeCreators API. Headlines, descriptions, impressions, regions, creative variations, OCR text.
Instagram — via ScrapeCreators API. Reels search, profile data, user reels with play counts, built-in transcription. Viral ratio ranking (views / followers) for identifying breakout content.
TikTok — via ScrapeCreators API. Keyword and hashtag video search, creator profiles, video comments with keyword filtering. Viral ratio ranking for identifying breakout content.
YouTube — via ScrapeCreators API. Niche search across videos and shorts, channel details with subscriber counts, top videos with views/likes/comments, all engagement signals expressed as % of subscribers.
Gemini AI — optional. Batch image/video analysis with visual descriptions, full verbatim transcripts, and messaging theme classification.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/thedavidquan01/ad-library-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server