Launching today
adextract
ad intelligence for AI agents
12 followers
ad intelligence for AI agents
12 followers
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 more. Claude connects with OAuth - paste the URL and your agent reads ads in under a minute.
How does the pricing scale if I want to pull a high volume of ads daily across all four platforms, and is there any rate-limit pain I should expect from the underlying ad libraries?
@okanmawx we have a tier based credit plan upto 10,000 credits. each credit is one search. No rate limit pain as we take care of rotating the IPs
How does the data freshness actually compare to the platforms themselves, especially for TikTok where ads cycle pretty fast? And is there any limit on how many ads an agent can pull per query, or does the MCP endpoint just stream whatever's available?
@beratnwzz Data freshness: Results reflect what's live on the ad libraries at query time - we call the platforms directly, no caching layer. For TikTok specifically, ads appear as soon as they're surfaced in the TikTok Ad Library. If a campaign stops, it drops. You're seeing what's active now.
Per-query limits: Each search returns up to 50 ads. Your agent can paginate through - ask for "page 2" and it fetches the next batch. No hard ceiling within your credit balance. One search = one credit
Streaming: The endpoint returns structured JSON, not a stream. Your agent gets the results, parses them, and can query deeper - read a specific ad, compare creatives across platforms, or filter by advertiser. you find more info on our docs - https://adextract.co/documentation
I kept running into the same issue: public ad libraries exist, but cross-platform ad research is still painful. Different UIs, different filters, different workflows, and a lot of manual effort to compare anything properly.
adextract makes that available through one MCP endpoint so agents can do the research across Meta, TikTok, LinkedIn, and Google from one place.
Would love to know what part of ad research you would hand off to an agent first.