Atlas Data MCP Server

Atlas Data MCP: ad library, jobs and Google Trends scrapers for AI agents

Eight production scrapers from Atlas Data, exposed as MCP tools so Claude, Cursor, VS Code or any MCP client can pull competitor ads (Google, Meta, LinkedIn, TikTok), job postings (Indeed, Google Jobs, Glassdoor) and Google Trends as clean JSON.

Nothing to install or host. The tools run as pay-per-result Apify Actors behind Apify's hosted MCP server, billed to your own Apify account. This repository holds the client configs, the MCP Registry metadata and guides.

Tools

Each run also has a small start fee ($0.0005 to $0.02, see the Store page). Prices are the Actors' current pay-per-event prices; the Store page is authoritative.

Apify's MCP server also adds its generic helpers (get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run) so an agent can page through large results.

Endpoint

https://mcp.apify.com/?tools=atlasdata/google-ads-transparency-scraper-reliable,atlasdata/facebook-ad-library-scraper-reliable,atlasdata/linkedin-ad-library-scraper-reliable,atlasdata/tiktok-ad-library-scraper-reliable,atlasdata/indeed-jobs-scraper-reliable,atlasdata/google-jobs-scraper-reliable,atlasdata/glassdoor-jobs-scraper-reliable,atlasdata/google-trends-scraper-reliable

• Transport: Streamable HTTP
• Auth: Apify OAuth (clients that support remote OAuth open a sign-in window) or an Apify API token sent as Authorization: Bearer <token>. Get a token at console.apify.com/settings/integrations.
• Fewer tools: remove entries from tools=. Each entry is atlasdata/<actor-name>. For example ads only: https://mcp.apify.com/?tools=atlasdata/google-ads-transparency-scraper-reliable,atlasdata/facebook-ad-library-scraper-reliable,atlasdata/linkedin-ad-library-scraper-reliable,atlasdata/tiktok-ad-library-scraper-reliable

Connect

Cursor

~/.cursor/mcp.json (global) or .cursor/mcp.json (project). With OAuth the URL is enough (configs/cursor-mcp.json):

{
  "mcpServers": {
    "atlas-data": {
      "url": "https://mcp.apify.com/?tools=atlasdata/google-ads-transparency-scraper-reliable,atlasdata/facebook-ad-library-scraper-reliable,atlasdata/linkedin-ad-library-scraper-reliable,atlasdata/tiktok-ad-library-scraper-reliable,atlasdata/indeed-jobs-scraper-reliable,atlasdata/google-jobs-scraper-reliable,atlasdata/glassdoor-jobs-scraper-reliable,atlasdata/google-trends-scraper-reliable"
    }
  }
}

With a token instead (configs/cursor-mcp-token.json):

{
  "mcpServers": {
    "atlas-data": {
      "url": "https://mcp.apify.com/?tools=atlasdata/google-ads-transparency-scraper-reliable,atlasdata/facebook-ad-library-scraper-reliable,atlasdata/linkedin-ad-library-scraper-reliable,atlasdata/tiktok-ad-library-scraper-reliable,atlasdata/indeed-jobs-scraper-reliable,atlasdata/google-jobs-scraper-reliable,atlasdata/glassdoor-jobs-scraper-reliable,atlasdata/google-trends-scraper-reliable",
      "headers": { "Authorization": "Bearer ${env:APIFY_TOKEN}" }
    }
  }
}

Claude Desktop

Custom connector (OAuth): Settings → Connectors → Add custom connector, name it Atlas Data, paste the endpoint URL and sign in to Apify.

Config file with a token: Settings → Developer → Edit Config, then add this to claude_desktop_config.json (uses mcp-remote, Node.js 18+; configs/claude_desktop_config.json):

{
  "mcpServers": {
    "atlas-data": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.apify.com/?tools=atlasdata/google-ads-transparency-scraper-reliable,atlasdata/facebook-ad-library-scraper-reliable,atlasdata/linkedin-ad-library-scraper-reliable,atlasdata/tiktok-ad-library-scraper-reliable,atlasdata/indeed-jobs-scraper-reliable,atlasdata/google-jobs-scraper-reliable,atlasdata/glassdoor-jobs-scraper-reliable,atlasdata/google-trends-scraper-reliable", "--header", "Authorization:${AUTH_HEADER}"],
      "env": { "AUTH_HEADER": "Bearer <your-apify-token>" }
    }
  }
}

Restart Claude Desktop afterwards.

Claude Code

claude mcp add --transport http atlas-data \
  "https://mcp.apify.com/?tools=atlasdata/google-ads-transparency-scraper-reliable,atlasdata/facebook-ad-library-scraper-reliable,atlasdata/linkedin-ad-library-scraper-reliable,atlasdata/tiktok-ad-library-scraper-reliable,atlasdata/indeed-jobs-scraper-reliable,atlasdata/google-jobs-scraper-reliable,atlasdata/glassdoor-jobs-scraper-reliable,atlasdata/google-trends-scraper-reliable" \
  --header "Authorization: Bearer $APIFY_TOKEN"

VS Code (Copilot agent mode)

.vscode/mcp.json (configs/vscode-mcp.json):

{
  "inputs": [{ "type": "promptString", "id": "apify-token", "description": "Apify API token", "password": true }],
  "servers": {
    "atlas-data": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=atlasdata/google-ads-transparency-scraper-reliable,atlasdata/facebook-ad-library-scraper-reliable,atlasdata/linkedin-ad-library-scraper-reliable,atlasdata/tiktok-ad-library-scraper-reliable,atlasdata/indeed-jobs-scraper-reliable,atlasdata/google-jobs-scraper-reliable,atlasdata/glassdoor-jobs-scraper-reliable,atlasdata/google-trends-scraper-reliable",
      "headers": { "Authorization": "Bearer ${input:apify-token}" }
    }
  }
}

Any other MCP client

Add a remote Streamable HTTP server with the endpoint above and the Authorization header. Clients that only speak stdio can use npx -y mcp-remote <URL> --header "Authorization:${AUTH_HEADER}". Coding agents can follow llms-install.md.

Example prompts

• "Which Google ads has hubspot.com run in Germany since September? Group them by format."
• "Pull the active Facebook and Instagram ads for Allbirds in the US and list the offers in the ad copy."
• "Get HubSpot's LinkedIn ads from the last 30 days and summarise the main calls to action."
• "Find TikTok video ads mentioning protein bar in France and list their landing pages."
• "Get 100 data engineer jobs on Indeed in Austin, TX posted in the last 3 days and give me the salary range."
• "Compare Glassdoor salary ranges for product manager in London and Berlin."
• "Compare Google Trends interest for notion, obsidian and logseq in the US over 12 months and list rising related queries."

Use cases

• Competitor ad monitoring: every ad a brand runs on Google, Meta, LinkedIn and TikTok, refreshed on a schedule.
• Agency pitches and QBRs: messaging, offers, landing pages and new markets for a client's competitors.
• Hiring signals and job market data: where a company is hiring, which roles, at what salary.
• Job boards and aggregators: clean Indeed, Google Jobs and Glassdoor feeds with apply links.
• Demand research: Google Trends interest by time and region before launching a product, market or campaign.

Calling the same tools from code (no MCP)

The tools are ordinary Apify Actors. One HTTP call runs an Actor and returns the items:

curl -X POST "https://api.apify.com/v2/acts/atlasdata~google-ads-transparency-scraper-reliable/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" -H "Content-Type: application/json" \
  -d '{"searchTerms": ["hubspot.com"], "region": "US", "maxAdsPerSearch": 20}'

Python (pip install apify-client, v3):

import os
from apify_client import ApifyClient

client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("atlasdata/indeed-jobs-scraper-reliable").call(
    run_input={"keywords": ["data engineer"], "location": "Austin, TX", "country": "us", "maxResults": 50}
)
for job in client.dataset(run.default_dataset_id).iterate_items():
    print(job["title"], "|", job["companyName"], "|", job.get("salaryMin"), job.get("salaryPeriod"))

More examples (Python, Node.js, curl) live in the per-tool repositories: google-ads-transparency-scraper, linkedin-ad-library-scraper, tiktok-ads-library-scraper, indeed-jobs-scraper, google-jobs-scraper, google-trends-scraper.

Guides

• Ask Claude or Cursor which ads your competitors are running (web)
• How to track a competitor's TikTok and Google ads (web)
• How to pull Indeed job data via API (web)
• On dev.to: Track a competitor's ads on Google, LinkedIn and TikTok with Python · Monitor Google Trends on a schedule and stop fighting 429s · Build a small job-market tracker with Google Jobs, Python and SQLite · Compare salaries and hiring across countries with Glassdoor job data and Python

Cost control

Every run is billed per result to the Apify account that authenticates. Keep maxAdsPerSearch / maxResults small while testing, and set a monthly usage limit in Apify Console if an agent runs unattended.

Registry metadata

server.json describes the suite for the official MCP Registry as com.getatlasdata/scrapers (domain-verified for getatlasdata.com). Publishing runs from the publish workflow. An earlier entry, io.github.AtlasDataDenmark/atlas-data, lists the first five tools.

About

Atlas Data builds fault-tolerant data pipelines for humans and AI agents, and competitor intelligence reports for agencies: getatlasdata.com · hello@getatlasdata.com · Apify Store.

Questions or bugs: open an issue here or in the matching tool repository.

License

Configs, docs and guides in this repository are MIT licensed. The tools themselves are hosted services on Apify.