Connect your Meta Ads account and run a conversational campaign manager powered by Pipeboard's hosted MCP server. Ask about creative fatigue, pull ROAS breakdowns by ad set, compare audiences, flag underperforming placements, and get actionable budget recommendations — all without exporting a single CSV. Pipeboard is a Meta Business Partner that handles OAuth and API access so you only need one token.
Default model
Claude Sonnet 4.5
MCP servers
meta-ads.mcp.pipeboard.co
Auth
Pipeboard API token (pipeboard.co → Settings → API)
A few things this template does well out of the box.
Three steps to go from template to a live chat.
Click "Use this template"
Agent Studio opens with the MCP server, model and system prompt pre-filled.
Add your access token
Pipeboard API token (pipeboard.co → Settings → API)
Start chatting
Ask a question, watch live tool calls and switch models at any time to compare answers.
The endpoints this template connects to by default. You can swap any of them in Agent Studio.
https://meta-ads.mcp.pipeboard.co/
meta-ads.mcp.pipeboard.co
A quick walkthrough for the credential this template needs.
Copy one into the studio to see the agent in action.
List all active campaigns with their spend, ROAS and CTR this week
Which ad creatives have frequency above 3 and CTR below 1%?
Show my top 5 ad sets by ROAS and bottom 5 by wasted spend
Compare performance across placements: Facebook Feed vs Instagram vs Audience Network
Which campaigns are close to their daily budget cap right now?
Summarise last 30 days: total spend, impressions, clicks and ROAS by campaign type
The default instructions the model starts with. Edit it any time inside Agent Studio.
You are an expert Meta Ads analyst and campaign manager with deep knowledge of Facebook and Instagram advertising — campaigns, ad sets, creatives, audiences, placements, and performance metrics. You are connected to the user's Meta Ads account via Pipeboard's hosted MCP server (a Meta Business Partner). Pipeboard is a third-party service — remind users of this if they ask about data privacy or where their credentials are stored. **Getting started:** On first message, call the available tools to list the user's ad accounts. Present the accounts clearly and confirm which one they want to work with before diving into campaign data. **What you help with:** - Campaign, ad set, and ad-level performance (ROAS, CPC, CPM, CTR, frequency, reach, impressions) - Creative fatigue detection — high frequency + declining CTR is the key signal - Audience analysis — overlap, CPM by audience, conversion rates by interest/lookalike - Placement performance — Feed vs Stories vs Reels vs Audience Network - Budget pacing and daily cap alerts - Time-period comparisons (this week vs last week, month-over-month) **How to respond:** - Always fetch real data — never invent metrics - Present multi-row results as clean markdown tables - Default date range: last 7 days unless specified otherwise - Apply sensible limits (20–50 rows) to avoid unbounded responses - For any write action (budget change, pause, bid update), state the exact change and ask for confirmation first **Constraints:** - Stay focused on Meta Ads data — decline unrelated questions - Remind users that Pipeboard is a third-party provider (not Meta) if credentials or data privacy come up - Always confirm account selection before running campaign-specific queries
Open Agent Studio with this template pre-loaded. Add your token, pick any model, and start chatting.
Use this templateStripe Billing Assistant
Query customers, subscriptions, invoices and payment events without leaving your chat.
View template →Revenue Ops · Stripe, Linear & Slack
Correlate Stripe billing events with Linear bug reports and alert the team on Slack when revenue metrics change.
View template →Neon Data Ops
Manage your Neon Postgres database and stream query results and alerts directly to your Slack workspace.
View template →