facebook-ads-library-mcp

Provides a Model Context Protocol (MCP) server that lets an AI agent search and retrieve information from Facebook’s public Ads Library by brand/page (via ScrapeCreators), and optionally analyze ad images/videos (video analysis via Google Gemini). Includes caching, request deduplication, and batch-oriented tools for platform IDs, ad retrieval, and (for videos) batched analysis.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml mcp facebook ads-library marketing-analytics python ai-analysis caching batch-processing
⚙ Agent Friendliness
69
/ 100
Can an agent use this?
🔒 Security
56
/ 100
Is it safe for agents?
⚡ Reliability
35
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
72
Documentation
70
Error Messages
--
Auth Simplicity
85
Rate Limits
65

🔒 Security

TLS Enforcement
70
Auth Strength
55
Scope Granularity
30
Dep. Hygiene
45
Secret Handling
75

Uses environment variables via a .env file for API keys (reduces risk of embedding secrets in code). No details are provided about TLS verification, secret logging, or dependency scanning; thus dependency hygiene and deeper security controls can’t be confirmed from the README alone.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
55
AF Security Reliability

Best When

You need agent-driven, programmatic access to Ads Library results plus optional LLM-based creative analysis, and you can provide the required ScrapeCreators (and optionally Gemini) API keys.

Avoid When

You need a turnkey hosted API with no local configuration, or you cannot manage external API credits/rate limits, or you require formal SDK/OpenAPI contracts for strict integration.

Use Cases

  • Find how many ads a brand is currently running and split by creatives (video vs image)
  • Summarize current ad messaging/themes for a specific company or brand
  • Compare advertising strategies across multiple brands
  • Perform creative analysis of ad images (composition, colors, text elements)
  • Perform creative/insight analysis of ad videos using Gemini
  • Cache reuse and media cache inspection/cleanup to reduce repeated work

Not For

  • Using Facebook/Ads Library data for purposes that violate platform terms, privacy expectations, or applicable laws
  • Automated large-scale extraction without rate-limit/credit management controls
  • Replacing human legal/brand compliance review when producing marketing conclusions

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Environment variables (SCRAPECREATORS_API_KEY, optional GEMINI_API_KEY)
OAuth: No Scopes: No

Auth is handled via API keys loaded from a local .env file. No OAuth flow or fine-grained scope model is described.

Pricing

Free tier: No
Requires CC: No

Pricing is not described here; usage likely depends on ScrapeCreators API credits and (for video analysis) Gemini API costs.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Documented

Known Gotchas

  • Video analysis requires GEMINI_API_KEY; image analysis tools likely work without it.
  • Operations depend on ScrapeCreators API credits; credit exhaustion may interrupt workflows and requires manual top-up.
  • Rate limits may require waiting; large batch requests can increase likelihood of hitting limits.
  • Local MCP server requires correct venv/Python path and .env placement; misconfiguration will prevent tool execution.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for facebook-ads-library-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6475
Packages Evaluated
19928
Need Evaluation
586
Need Re-evaluation
Community Powered