- Home
- MCP Integrations
- Foreplay MCP Server
Foreplay MCP Server
Connect to the Foreplay MCP server to search competitor ads across 8 platforms, browse any brand’s ad library, and analyze creative strategies using AI agents on Gumloop, Claude, or Cursor.
Try Foreplay now
Type what you want done. Sign in and run it live with an AI agent.

Installation
Set up the Foreplay MCP server in Gumloop
Do this once to provision your hosted server URL.
Create a Gumloop account
To use this MCP, you need a Gumloop account. If you don't have one yet, sign up and start a 14-day free trial.
Add and authorize the Foreplay server
In Gumloop, open Connectors and add Foreplay. Paste your Foreplay API key when prompted. The credential is stored securely in Gumloop.
Then use it in your client
Use in GumloopUse Foreplay in an agent
Once Foreplay is set up, just open any Gumloop agent, add Foreplay as a connector, and start chatting with the agent.
Tools (5)
Search Brands
3 per itemSearch for brands by domain name OR brand name. Provide both parameters to get merged results from both search types.
Search And Filter Ads
3 per itemSearch and filter ads by text content, date ranges, platforms, formats, niches, market targets, and languages. Leave query empty to filter without text search.
Get Ads By Brand Or Page
3 per itemGet ads for specific brand IDs or Facebook page ID with filtering options. Provide either brand_ids or page_id parameter.
Get Brand Analytics
5 per itemGet comprehensive analytics data for a brand or Facebook page including running ads distribution and creative velocity over a date range.
Get Ad Details
5 creditsGet comprehensive details of a specific ad by its ID including metadata, creative content, targeting info, and performance data.
What is Foreplay MCP?
The Foreplay MCP server gives AI agents access to Foreplay’s ad intelligence database. That means agents can search for brands, search ads across eight platforms with rich filters, browse any brand’s full ad library, analyze a brand’s creative velocity over time, and pull deep details on a single ad, including its emotional driver scores. It’s a research tool so AI agents can answer questions about what ads competitors are running and why they are (or aren’t) working.
If you spend time scrolling ad libraries, screenshotting competitor creatives, or piecing together which formats a brand is testing, an AI agent can take over a lot of that research. Describe what you need, and your AI agent will surface the ads and patterns for you.
MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of getting a Foreplay API key, writing code against the Foreplay API, and handling its filters and pagination yourself, you connect the built-in Foreplay connection on Gumloop. After that, you research ads just by asking your AI agent in plain language.
Related MCP servers
Google Ads MCP Server
Interact with Google Ads accounts, campaigns, and reports
Google DV360 MCP Server
Interact with Google Display & Video 360 campaigns, line items, and performance data
Semrush MCP Server
Access Semrush SEO and digital marketing analytics data
Google Analytics MCP Server
Run reports, manage accounts and properties, configure custom dimensions, metrics and conversions, and send server-side events on Google Analytics.
Google Sheets MCP Server
Read, write and update your Google Sheets
Slack MCP Server
Interact with Slack channels and messages
What you can do with Foreplay MCP on Gumloop
Search and discover brands
Find any advertiser by domain or name with fuzzy matching, and get a brand profile with its category, niches, and verification status. A quick way to point an agent at the right competitor.
Search ads across eight platforms
Run a full-text search through ad copy across Facebook, Instagram, TikTok, YouTube, LinkedIn, Threads, Audience Network, and Messenger, filtered by format, niche, B2B or B2C, language, date range, and live status. One query spans your whole competitive set.
Browse a brand’s ad library
Pull every ad for a specific brand or Facebook page, filtered by format, platform, live status, and date. See exactly what a competitor is running right now or has run before.
Analyze creative velocity
Get a brand’s daily active and inactive ad counts, broken down by creative format, over a 30-day window. An agent can tell you how aggressively a competitor is advertising and which formats they’re testing.
Surface winning creatives
Sort by longest-running to find the ads a brand has kept live the longest, a strong signal for what’s working, and filter to live ads only to focus on what’s in market today.
Deep-dive into a single ad
Retrieve full details on any ad: creative content, targeting, CTA type, media URLs, running duration, and emotional driver scores for achievement, engagement, and esteem. Useful for creative analysis and strategy recommendations.
How to connect the Gumloop Foreplay MCP Server
- 1
Create a Gumloop account
Sign up at gumloop.com. Every new account starts with a 14-day free trial.
- 2
Add the Foreplay MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Foreplay in your AI workflows
That's it. Your AI agent can now search ads, browse brand libraries, and analyze creative strategies across eight platforms. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Foreplay MCP use cases
Competitor ad monitoring for performance marketers
An AI agent can track a competitor’s live ads and creative velocity on a schedule, flag when they launch a new format or ramp up spend signals, and post a weekly summary to Slack or a Google Sheet. Teams see competitive moves as they happen instead of stumbling on them.
Creative research and briefs for strategists
Ask an agent to find the longest-running ads in your niche, read their emotional driver scores and CTAs, and compile the patterns into a creative brief. A faster path from researching "What’s working out there?" to finding a concrete set of angles to test.
Market landscape analysis for agencies
Pull the brands in a category, browse their ad libraries, and have an agent summarize which platforms and formats each one leans on. A quick competitive landscape for a pitch or a quarterly review.
New-campaign inspiration
Before a launch, an agent can search top ads by format, platform, and B2B or B2C target, then summarize the hooks, formats, and CTAs that recur, so the team starts from evidence instead of a blank page.
Cross-platform creative trend reports
Combine Foreplay with Google Sheets and Slack in a single agent: pull ads across eight platforms for a set of brands, analyze emotional drivers and formats, and output a shareable trend report your whole team can reference.
Why use Gumloop for Foreplay MCP
Built-in connection, no API key to manage
Building your own Foreplay MCP server means getting an API key, wiring up the Foreplay API’s filters and pagination, and writing code to parse results. Gumloop comes with the Foreplay connection built in, so you can start searching ads right away. No API key, no config files, and no code against the Foreplay API.
Works with multiple MCP clients
Use the Foreplay MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop. Same server URL, works with any MCP client.
Chain Foreplay with 100+ other integrations
Combine Foreplay with Google Ads, Google Sheets, Slack, and other MCP tools in a single AI agent. Research competitor ads, analyze them with an LLM, and drop the findings wherever your team works.
Enterprise-grade and scalable
Built for teams, with role-based permissions and dedicated support for Pro users. The Foreplay MCP is read-only and uses your credentials to access ad intelligence data, so agents only read what your account can.
Pricing with a free trial
You can test the Foreplay MCP integration during Gumloop’s 14-day free trial before committing. Paid plans start at $37/month.
Frequently asked questions
Ship Foreplay agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.