adextract
Ad libraries are public but fragmented. Every platform is a silo - different UI, different filters, different quirks. If you want to see what competitors are running, you're either opening four tabs and pasting into Excel, or maintaining scrapers that rot with every layout change. adextract gives AI agents a single MCP endpoint to search, read, and compare ads across Meta, TikTok, LinkedIn, and mo
README
Adextract MCP Server
Connect AI assistants to Adextract — search ad libraries across Meta, Google Ads, LinkedIn, and TikTok, plus creative analysis with ad_reader.
Hosted endpoint: https://mcp.adextract.co/mcp
Installation
Hosted MCP (recommended)
Connect to the Adextract hosted server:
https://mcp.adextract.co/mcp
Get your API key at adextract.co (account → API keys).
Cursor
Add to ~/.cursor/mcp.json or project .cursor/mcp.json:
{
"mcpServers": {
"ad-extract": {
"url": "https://mcp.adextract.co/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
VS Code
Add to .vscode/mcp.json:
{
"servers": {
"ad-extract": {
"type": "http",
"url": "https://mcp.adextract.co/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Claude Web (OAuth)
- Open Claude → Settings → Connectors → Add custom connector
- Name:
ad-extract - URL:
https://mcp.adextract.co/mcp - Sign in and approve when prompted — no API key in the URL.
Claude Desktop (mcp-remote)
{
"mcpServers": {
"ad-extract": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.adextract.co/mcp",
"--header",
"Authorization: Bearer YOUR_API_KEY"
]
}
}
}
More clients and config paths: docs/CLIENT_SETUP.md
Available Tools
| Tool | Platform | Description |
|---|---|---|
search_meta_ads |
Meta | Search Facebook & Instagram ads |
search_meta_pages |
Meta | Discover pages and location IDs |
get_meta_page_info |
Meta | Page transparency and metadata |
get_meta_ad_details |
Meta | EU/UK ad transparency details |
search_google_ads |
Google Ads Transparency Center | |
search_google_ads_advertisers |
Advertiser and domain search | |
get_google_ad_details |
Creative details | |
get_google_ads_advertiser_info |
Advertiser profile from Search ads | |
search_linkedin_ads |
LinkedIn Ad Library | |
search_tiktok_ads |
TikTok | TikTok Ads Library |
search_tiktok_advertisers |
TikTok | TikTok advertiser discovery |
get_tiktok_ad_details |
TikTok | Targeting and creative details |
ad_reader |
All | Analyze image/video creatives (format, audience, emotion, archetypes) |
Full reference: docs/TOOLS.md
Prompts & Resources
Built-in MCP prompts for common workflows:
adextract_top_ads_for_brandadextract_competitor_benchmarkadextract_channel_strategyadextract_analyze_ad_urladextract_schedule_watchlist
Resources include agent skill instructions and prompt-pack references (adextract://skill/main, etc.).
Authentication
| Method | Best for |
|---|---|
| OAuth 2.0 | Claude Web and OAuth-capable connectors |
| Bearer API key | Cursor, VS Code, Claude Desktop, mcp-remote |
Discovery endpoints:
https://mcp.adextract.co/.well-known/oauth-protected-resourcehttps://mcp.adextract.co/oauth/.well-known/oauth-authorization-server
Server card (registry / client discovery):
https://mcp.adextract.co/.well-known/mcp.json
Example prompts
Show me the latest Nike ads on Facebook in the US.
→ search_meta_ads({ q: "nike", country: "US", active_status: "active" })
Find Google ads for tesla.com from the last 30 days.
→ search_google_ads({ domain: "tesla.com", time_period: "last_30_days" })
Analyze this ad creative URL with ad_reader.
→ ad_reader({ url: "https://..." })
Documentation
| Doc | Purpose |
|---|---|
| docs/CLIENT_SETUP.md | Per-client configuration |
| docs/TOOLS.md | Tools, prompts, resources |
| docs/TROUBLESHOOTING.md | Common errors and fixes |
| REGISTRY_CHECKLIST.md | Pre-submission checklist |
| SECURITY.md | Security policy |
| SUPPORT.md | How to get help |
Links
- Website: adextract.co
- MCP endpoint:
https://mcp.adextract.co/mcp - Repository: github.com/ad-vertly/adextract-mcp-server
Built with ❤️ by Adextract
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。