Ad Library MCP

14 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated:

0 can modify or destroy data
14 read-only
14 tools total

Community server · catalogue entry verified 03/07/2026

How to control Ad Library MCP ↓

What Ad Library MCP exposes to your agents

Read (14) Write / Execute (0) Destructive / Financial (0)

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

How to control Ad Library MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Ad Library MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations
{
  "analyze-creatives": {
    "limits": [
      {
        "counter": "analyze-creatives_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Ad Library MCP — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON AD LIBRARY →

Instant setup, no code required.

All 14 Ad Library MCP tools

READ 14 tools
Read analyze-creatives Batch analyze ad creatives (images and videos) using Gemini AI. Returns visual descriptions, text overlays, em Read google-get-ad Get full details for a specific ad from Google Ads Transparency Center by URL. Returns creative variations (he Read google-search-ads List ads from Google Ads Transparency Center by company domain or advertiser ID. Returns ad format, images, da Read ig-get-profile Get an Instagram creator\ Read ig-get-transcript Transcribe an Instagram Reel. Uses ScrapeCreators built-in transcript (1 credit, fast). Falls back to Gemini A Read ig-search-reels Search Instagram Reels by keyword, ranked by viral ratio (views / followers). High ratio = content broke out b Read meta-get-ad Get full details for a specific ad from the Meta Ad Library by ID or URL. Returns creative assets (video/image Read meta-search-ads Search the Meta Ad Library by keyword or company name. For company searches, automatically resolves the compan Read resolve-company Find a company\ Read tiktok-get-comments Get comments from a TikTok video, sorted by likes. Optional keyword filter to find specific audience reactions Read tiktok-get-profile Get a TikTok creator\ Read tiktok-search-videos Search TikTok videos by keyword or hashtag (), ranked by viral ratio (views / followers). High ratio = content Read youtube-get-profile Get a YouTube creator\ Read youtube-search-creators Search YouTube for creators in a niche, ranked by views-per-subscriber (median across surfaced videos). Return

Questions about Ad Library MCP

Is the Ad Library MCP server safe to use without restrictions? +

The Ad Library MCP server is primarily read-only with 14 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Ad Library MCP server expose? +

14 tools across 2 categories: Read, Write. 14 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Ad Library MCP? +

Register the Ad Library MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ad Library MCP tool call.

Deterministic rules across all 14 Ad Library MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

14 Ad Library MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.