Search and explore ads at scale, uncover competitor strategies, and pull actionable brand analytics directly into your workflows. Foreplay helps marketers and creative teams find winning ad ideas faster, analyze what works, and operate with confidence across platforms.
Explore more than 100 million live and historical ads across major platforms for instant inspiration and competitive research.

​
What is Foreplay MCP?

The Foreplay MCP creates an AI-powered node that understands the Foreplay API. You describe what you need, the node calls the right endpoint, and returns structured data you can pass to the next steps in your Gumloop workflow.

​
What Can It Do for You?

  • Find brands by name or domain and return clean, structured profiles
  • Discover and filter ads by text, platform, format, niche, market, language, and date ranges
  • Retrieve ads for a specific brand or Facebook page with advanced filters
  • Pull brand analytics like running ads distribution and creative velocity over time

​
Available Tools

ToolWhat It DoesExample Use
Search BrandsSearch for brands by domain name or brand name, with merged results and detailed brand fields”Search for brand matching brand name or domain and return structured data with brand id, brand name, domain, and associated platform pages”
Search And Filter AdsSearch and filter ads by text content, date ranges, platforms, formats, niches, markets, and languages”Find ads containing search text on platform between start date and end date and return ad id, brand name, platform, created date, caption, and ad url”
Get Ads By Brand Or PageGet ads for a specific brand id or Facebook page id with advanced filtering options”Using brand id, get ads on platform between start date and end date and return ad id, platform, created date, and creative url”
Get Brand AnalyticsRetrieve analytics for brands, including running ads distribution and creative velocity over a date range”Using brand id, get analytics from start date to end date and return running ads distribution by platform and creative velocity”
Get Ad DetailsGet comprehensive details for specific ads including metadata, creative content, targeting info, and performance data”Using ad id, return structured data with ad text, creative type, media url, platform, start date, end date, and available performance metrics”

​
Credit Costs

ToolCredits Per Use
Search Brands3 per item
Search And Filter Ads3 per item
Get Ads By Brand Or Page3 per item
Get Brand Analytics5 per item
Get Ad Details5 per item

​
How to Use

1

Create Your Foreplay MCP Node

Go to your node library, search for Foreplay, and click “Create a node with AI”
2

Add Your Prompt

Drag the Foreplay MCP node to your canvas and add your prompt in the text box.
3

Test Your Node

Run the node to see the results. If it works as expected, you’re all set! If you run into issues, check the troubleshooting tips below.
4

Save and Reuse

Once your Foreplay MCP node is working, save it to your library. You can now use this customized node in any workflow.

​
Example Prompts

Here are some prompts that work well with Foreplay MCP: Brand Lookup: 
Search for brand matching `brand name` or `domain` and return structured data with brand id, brand name, domain, and associated platform pages
Ad Discovery: 
Find ads containing `search text` on `platform` between `start date` and `end date`, filter by format `format`, and return ad id, brand name, platform, created date, caption, and ad url
Brand Ads Retrieval: 
Using `brand id`, get ads on `platform` in `date range` and return ad id, created date, creative type, and creative url
Brand Analytics: 
Using `brand id`, get analytics for `start date` to `end date` and return running ads distribution by platform and creative velocity
Start with one action per node. First get the brand id, then retrieve ads, then analyze with Ask AI. Focused nodes run faster, are easier to debug, and are perfect for reuse across multiple workflows.

​
Troubleshooting

If your Foreplay MCP node isn’t working as expected, try these best practices:

​
Keep Prompts Simple and Specific

  • Good: “Search for brand name and return id and domain”
  • Bad: “Search for brand name, get their top ads from date range, analyze the best hook, and draft an email to recipient email”
For better results, keep each node focused on a single action. You can chain multiple nodes to accomplish multi-step goals.

​
Match What Foreplay Can Do

  • Good: “Find ads containing search term on platform between start date and end date and return ad id and creative url”
  • Bad: “Download each ad video, trim it, add captions, and publish to social”
Foreplay MCP excels at ad discovery and analytics. For media processing, combine it with Run Code or Call API. To publish or message, connect Gmail Sender/Reader or Slack Message Sender/Reader.

​
Break Complex Tasks Into Steps

Attempting everything in one prompt can cause timeouts or partial results: 
Search ads for all brands matching `industry type`, filter to top creatives, analyze themes, and email a summary to `recipient email`
A more efficient approach is to break this into smaller nodes:
1

Step 1: Find Brands

Search for brands matching industry type and return structured data with brand names and ids
2

Step 2: Get Ads

Using brand ids and date range, get ads on platform and return ad ids, created dates, captions, and creative urls
3

Step 3: Analyze Creative Themes

Using the ad data, summarize themes and patterns and return key takeaways and examples using Ask AI node
Connect these nodes sequentially in your workflow. The structured data from one step becomes the input for the next.

​
Focus on Data Retrieval

Foreplay MCP is ideal for gathering structured data. For analysis or content creation, pair it with other nodes. Example:
  • Good prompt: “Using brand id, get analytics from start date to end date and return running ads distribution and creative velocity”
  • Bad prompt: “Get analytics, write a full report with recommendations, and send it to recipient email”
Use Ask AI node for writing and analysis, then connect Gmail Sender/Reader or Slack Message Sender to share your results.

​
Troubleshooting Node Creation

​
Need More Help?