ZuckerBot
50 tools for Meta Ads campaign management, creative analysis, audience building, and conversion tracking, accessible to any MCP-compatible AI agent.
README
<div align="center">
ZuckerBot
The Meta Ads toolkit for AI agents.
50 tools for campaign management, creative analysis, audience building, and conversion tracking. One npx command. Works with Claude, ChatGPT, OpenClaw, Cursor, and any MCP-compatible agent.
{
"mcpServers": {
"zuckerbot": {
"command": "npx",
"args": ["-y", "zuckerbot-mcp"],
"env": { "ZUCKERBOT_API_KEY": "zb_live_your_key_here" }
}
}
}
Get API Key (free) · npm · Docs · Website
</div>
Why ZuckerBot?
Your agent already writes code, manages files, and searches the web. It should manage your ads too.
ZuckerBot gives any AI agent full Meta Ads capabilities through MCP. No dashboard, no UI to learn, no platform to log into. Your agent installs it, connects your ad account, and gets to work.
What agents can do with ZuckerBot:
- Pull campaign performance and spot what's working
- Analyse ad creatives and recommend what to test next
- Build and launch campaigns with targeting and budget
- Create custom and lookalike audiences
- Set up server-side conversion tracking (CAPI)
- Research competitors, reviews, and market benchmarks
- Generate ad creative briefs and copy
How it works
You ↔ Your Agent (Claude, ChatGPT, OpenClaw, Cursor, etc.)
↕
ZuckerBot MCP
↕
Meta Marketing API
ZuckerBot handles the Meta API complexity. Your agent handles the conversation. You make the decisions.
Install
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"zuckerbot": {
"command": "npx",
"args": ["-y", "zuckerbot-mcp"],
"env": { "ZUCKERBOT_API_KEY": "zb_live_your_key_here" }
}
}
}
OpenClaw
Add to your MCP config:
{
"mcpServers": {
"zuckerbot": {
"command": "npx",
"args": ["-y", "zuckerbot-mcp"],
"env": { "ZUCKERBOT_API_KEY": "zb_live_your_key_here" }
}
}
}
Cursor / Windsurf / Any MCP Client
Same config pattern. ZuckerBot works with any client that supports the Model Context Protocol.
CLI (for humans)
npm install -g zuckerbot-mcp
zuckerbot preview https://your-business.com
zuckerbot meta status
zuckerbot create https://your-business.com --budget 5000 --objective leads
Tools (50)
Setup & Account (7)
| Tool | What it does |
|---|---|
quickstart |
Guided setup: check auth, show next steps, recommended tool flow |
meta_status |
Check Meta connection status for your API key |
list_ad_accounts |
List available Meta ad accounts and current selection |
select_ad_account |
Connect a specific ad account |
list_meta_pages |
List Facebook pages and current selection |
select_meta_page |
Set active page for ad delivery |
get_launch_credentials |
Verify all required credentials are set before launching |
Campaigns (9)
| Tool | What it does |
|---|---|
preview_campaign |
Generate ad preview from a URL (no Meta account needed) |
create_campaign |
Create a campaign draft with strategy, targeting, and creatives |
get_campaign |
Get campaign detail, workflow state, and linked creatives |
approve_campaign_strategy |
Approve tiers and creative angles for an intelligence campaign |
suggest_angles |
Get proposed creative angles and audience tiers for a draft |
activate_campaign |
Activate ready tiers and begin ad delivery |
launch_campaign |
Launch one or all variants from a draft on Meta |
pause_campaign |
Pause or resume a live campaign |
get_performance |
Real-time campaign metrics: spend, leads, CPL, CTR, ROAS |
Audiences (6)
| Tool | What it does |
|---|---|
create_seed_audience |
Build a custom audience from hashed CAPI users |
create_lookalike_audience |
Create a lookalike from any seed audience |
list_audiences |
List all custom and lookalike audiences |
refresh_audience |
Refresh an audience or sync latest state from Meta |
get_audience_status |
Check audience size, status, and readiness |
delete_audience |
Remove an audience from Meta and ZuckerBot |
Creatives (8)
| Tool | What it does |
|---|---|
generate_creatives |
Generate ad copy and images (or Kling video) |
request_creative |
Create a creative handoff package for production |
upload_creative |
Upload finished assets and provision paused Meta ads |
get_creative_status |
Check creative generation progress |
creative_analysis |
AI analysis of ad creative performance with recommendations |
creative_qa |
Quality check creatives against Meta ad policies |
generate_briefs |
Generate creative briefs based on performance data |
Conversion Tracking / CAPI (5)
| Tool | What it does |
|---|---|
capi_config |
Get or update server-side conversion tracking config |
capi_status |
7-day and 30-day CAPI delivery and attribution stats |
capi_test |
Send a test event through the CAPI pipeline |
sync_conversion |
Send lead quality feedback to Meta's algorithm |
list_pixels |
List and select Meta pixels for conversion tracking |
Portfolios (5)
| Tool | What it does |
|---|---|
create_portfolio |
Create an audience portfolio from a template |
launch_portfolio |
Launch all campaigns in a portfolio |
portfolio_performance |
Tier-by-tier portfolio performance breakdown |
rebalance_portfolio |
Dry-run or apply budget rebalancing across tiers |
Research (3)
| Tool | What it does |
|---|---|
research_reviews |
Review intelligence for any business |
research_competitors |
Competitor ad analysis by industry and location |
research_market |
Market intelligence and ad benchmarks |
Business Context (4)
| Tool | What it does |
|---|---|
enrich_business |
Crawl a website and cache structured business context |
upload_business_context |
Upload text content and extract business insights |
list_business_context |
List uploaded context files and summaries |
select_lead_form |
Select a lead form for campaign targeting |
Typical Agent Flow
1. Research → research_reviews + research_competitors (parallel)
2. Preview → preview_campaign (show user what ads look like)
3. Create → create_campaign (draft with strategy + targeting)
4. Approve → approve_campaign_strategy
5. Creative → request_creative or upload_creative
6. Activate → activate_campaign
7. Monitor → get_performance + creative_analysis
8. Optimise → sync_conversion + audience tools
Every tool returns a _hint field suggesting the logical next step, so your agent always knows what to do next.
ZuckerBot vs alternatives
| ZuckerBot | Pipeboard | AdAmigo.ai | Supermetrics | |
|---|---|---|---|---|
| What it is | Meta Ads toolkit for agents | Basic Meta MCP | Full ad management agent | Data extraction |
| Tools | 50 | ~20 | N/A (platform) | N/A (connectors) |
| Creative analysis | ✅ AI-powered | ❌ | ✅ Platform-only | ❌ |
| CAPI support | ✅ Full pipeline | ❌ | Partial | ❌ |
| Audience builder | ✅ Seed + LAL | ❌ | ✅ Platform-only | ❌ |
| Works with any agent | ✅ MCP standard | ✅ MCP standard | ❌ Locked to platform | ❌ |
| Price | Free tier available | Free | $349/mo/account | $39-299/mo |
Pricing
| Tier | Monthly | API Calls | Tools |
|---|---|---|---|
| Free | $0 | 1,000/mo | Read-only (performance, analysis, research) |
| Pro | $49 + 0.1% of ad spend | 50,000/mo | All tools including campaign management |
| Scale | $149 + 0.05% of ad spend | 500,000/mo | All tools + multi-account + priority rate limits |
Free tier gets you started. Pro pays for itself with one optimised campaign.
Example conversation
You: How are my Meta campaigns doing this week?
Agent calls
get_account_insights+creative_analysisAgent: You spent $2,340 across 4 campaigns this week. Your LAL campaign is crushing it at $28 CPL — that's 40% below your account average. But your broad targeting campaign is at $95 CPL and burning budget. The "customer testimonial" creative has a 3.2% CTR vs 1.1% for your product shots. I'd recommend pausing the broad campaign and shifting that budget to the LAL.
You: Do it.
Agent calls
pause_campaign+ (budget adjustment)
Development
git clone https://github.com/DatalisHQ/zuckerbot.git
cd zuckerbot/mcp-server
npm install
npm run build
npm start
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.