{
  "mcpServers": {
    "zuckerbot": {
      "command": "npx",
      "args": ["-y", "zuckerbot-mcp"],
      "env": { "ZUCKERBOT_API_KEY": "zb_live_your_key_here" }
    }
  }
}

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)

Campaigns (9)

Audiences (6)

Creatives (8)

Conversion Tracking / CAPI (5)

Portfolios (5)

Research (3)

Business Context (4)

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

Pricing

Free tier gets you started. Pro pays for itself with one optimised campaign.

Get your API key

Example conversation

You: How are my Meta campaigns doing this week?

Agent calls get_account_insights + creative_analysis

Agent: 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