Skip to content
Back to search

mcp-server

MCP server for the Meta Ad Library: give Claude, Cursor and other AI assistants access to Facebook and Instagram ads, creatives, EU transparency data and advertisers via ScrapeAdLibrary.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/scrapeadlibrary--mcp-server/badge.svg)](/listings/scrapeadlibrary--mcp-server)

HTML

<a href="/listings/scrapeadlibrary--mcp-server"><img src="/api/listings/scrapeadlibrary--mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Get an API Key

Sign up at [scrapeadlibrary.com](https://scrapeadlibrary.com) and create an API key (starts with `sal_`).

2. Configure Claude Desktop

Add to your `claude_desktop_config.json`:

{
  "mcpServers": {
    "scrapeadlibrary": {
      "command": "uvx",
      "args": ["scrapeadlibrary-mcp"],
      "env": {
        "SCRAPEADLIBRARY_API_KEY": "sal_your_key_here"
      }
    }
  }
}

3. Use it

Ask Claude: - "What ads is Nike running in Italy right now? Summarise their messaging." - "Show me active video ads about 'protein powder' in the US, sorted by impressions" - "Which advertisers run ads for 'running shoes'?" - "Get the EU reach and targeting of ad 1550534860016399"

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 142 lines
  1. # ScrapeAdLibrary MCP Server
  2. <!-- mcp-name: com.scrapeadlibrary/scrapeadlibrary -->
  3. An [MCP](https://modelcontextprotocol.io) server that lets AI assistants (Claude Desktop, Claude
  4. Code, Cursor, Cline...) search the public Meta Ad Library (Facebook, Instagram, Messenger, Audience
  5. Network, Threads) through the [ScrapeAdLibrary](https://scrapeadlibrary.com) API: competitor ads, creatives,
  6. advertisers, political ad spend, EU (DSA) reach and targeting.
  7. ## Features
  8. **5 Tools** — search ads, ad detail, advertiser profile, advertiser's ads, advertiser search
  9. **4 Documentation Resources** — API reference, quickstart, pricing, workflow examples
  10. **3 Prompt Templates** — competitor ad research, keyword market scan, single ad analysis
  11. ## Connect without installing (Claude, ChatGPT, Claude Code)
  12. The same tools are available as a hosted remote MCP server with OAuth sign-in: no API key to copy,
  13. nothing to install. Add this URL as a custom connector and sign in with your ScrapeAdLibrary account:
  14. ```
  15. https://api.scrapeadlibrary.com/mcp
  16. ```
  17. - **Claude** (web, Desktop, mobile): Customize → Connectors → Add custom connector.
  18. - **ChatGPT**: chatgpt.com/plugins → Add custom MCP server → OAuth.
  19. - **Claude Code**: `claude mcp add --transport http scrapeadlibrary https://api.scrapeadlibrary.com/mcp`,
  20. then `/mcp` to sign in.
  21. Calls use your account's credits with the API's pricing. Step-by-step guide:
  22. [scrapeadlibrary.com/docs/mcp](https://scrapeadlibrary.com/docs/mcp).
  23. ## Quick Start (local server with an API key)
  24. ### 1. Get an API Key
  25. Sign up at [scrapeadlibrary.com](https://scrapeadlibrary.com) and create an API key (starts with `sal_`).
  26. ### 2. Configure Claude Desktop
  27. Add to your `claude_desktop_config.json`:
  28. ```json
  29. {
  30. "mcpServers": {
  31. "scrapeadlibrary": {
  32. "command": "uvx",
  33. "args": ["scrapeadlibrary-mcp"],
  34. "env": {
  35. "SCRAPEADLIBRARY_API_KEY": "sal_your_key_here"
  36. }
  37. }
  38. }
  39. }
  40. ```
  41. ### 3. Use it
  42. Ask Claude:
  43. - "What ads is Nike running in Italy right now? Summarise their messaging."
  44. - "Show me active video ads about 'protein powder' in the US, sorted by impressions"
  45. - "Which advertisers run ads for 'running shoes'?"
  46. - "Get the EU reach and targeting of ad 1550534860016399"
  47. ## Configuration for Other Clients
  48. ### Cursor
  49. Add the same JSON block to `.cursor/mcp.json`.
  50. ### Claude Code
  51. ```bash
  52. claude mcp add scrapeadlibrary -e SCRAPEADLIBRARY_API_KEY=sal_your_key_here -- uvx scrapeadlibrary-mcp
  53. ```
  54. ## Installation Alternatives
  55. ### pip
  56. ```bash
  57. pip install scrapeadlibrary-mcp
  58. SCRAPEADLIBRARY_API_KEY=sal_xxx scrapeadlibrary-mcp
  59. ```
  60. ### npx
  61. ```bash
  62. SCRAPEADLIBRARY_API_KEY=sal_xxx npx scrapeadlibrary-mcp
  63. ```
  64. (The npm package is a thin wrapper: it runs the Python server via `uvx`, or `python3 -m` as a
  65. fallback.)
  66. ### Docker
  67. ```bash
  68. docker build -t scrapeadlibrary-mcp .
  69. docker run -i --rm -e SCRAPEADLIBRARY_API_KEY=sal_xxx scrapeadlibrary-mcp
  70. ```
  71. ## Tools
  72. | Tool | Description | Cost | Key defaults |
  73. |------|-------------|------|--------------|
  74. | `search_ads` | Search ads by keyword and/or advertiser, with country, status, media, platform, language, date filters | 1 credit per 10 ads | limit=10, status=active |
  75. | `get_ad` | Full ad: text, media, cards, advertiser, payer/beneficiary, EU/UK transparency | 2 credits | — |
  76. | `get_page` | Advertiser profile: category, likes, Instagram, active ads estimate | 1 credit | — |
  77. | `get_page_ads` | Ads of one advertiser | 1 credit per 10 ads | limit=10, status=active |
  78. | `search_pages` | Advertisers that ran ads matching a keyword | 1 credit per 10 results | limit=10 |
  79. Empty results and errors cost 0 credits. Lists return a `cursor` to fetch the next page.
  80. ## Environment Variables
  81. | Variable | Required | Description |
  82. |----------|----------|-------------|
  83. | `SCRAPEADLIBRARY_API_KEY` | Yes | Your API key (starts with `sal_`) |
  84. | `SCRAPEADLIBRARY_BASE_URL` | No | Override API base URL (default: `https://api.scrapeadlibrary.com`) |
  85. ## Development
  86. ```bash
  87. uv venv && uv pip install -e ".[dev]"
  88. .venv/bin/pytest
  89. .venv/bin/ruff check . && .venv/bin/ruff format --check .
  90. ```
  91. Test with MCP Inspector:
  92. ```bash
  93. SCRAPEADLIBRARY_API_KEY=sal_xxx .venv/bin/mcp dev dev_server.py
  94. ```
  95. `assets/logo-400.png` is still the placeholder logo inherited from the template: replace it with
  96. the final brand logo before publishing to registries.
  97. ## License
  98. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.