PropellerAds MCP Server
Integrates PropellerAds' programmatic advertising platform with AI to automate campaign management, real-time optimization, and performance analysis. It enables users to create, scale, and manage ad campaigns through natural language commands for tasks like bid adjustment and zone blacklisting.
README
PropellerAds MCP Server
Democratizing Programmatic Advertising with AI
Transform your media buying with AI-powered campaign optimization. This MCP (Model Context Protocol) server integrates PropellerAds' powerful programmatic advertising platform with Claude, enabling automated campaign management, real-time optimization, and data-driven decision making.
Created by @jannafta | Website
Why PropellerAds MCP?
In the fast-paced world of programmatic advertising, success depends on quick decisions and continuous optimization. This MCP server brings the power of AI to your fingertips, allowing you to:
- Automate Campaign Management: Create, update, and optimize campaigns with natural language commands
- Real-time Performance Analysis: Get instant insights on ROI, CTR, conversions, and more
- Smart Optimization: AI-driven bid adjustments, creative rotation, and targeting refinement
- Scale Efficiently: Identify and capitalize on winning campaigns automatically
- Save Time: Focus on strategy while AI handles the repetitive tasks
Perfect for:
- Media Buyers and Performance Marketers
- iGaming Affiliates
- App Developers and Publishers
- Growth Hackers and Digital Agencies
- Anyone running PropellerAds campaigns
Quick Start
Prerequisites
-
PropellerAds Account: You need an active account with API access
- Minimum requirement: $1000 total spend or deposit
- Get your API token from: https://ssp.propellerads.com/#/app/profile
-
Claude Desktop: Install Claude Desktop app
- Download from: https://claude.ai/download
-
Python 3.10+: Required for the MCP server
Installation
Option 1: Install from PyPI (Recommended)
pip install propellerads-mcp
Option 2: Install from source
git clone https://github.com/JanNafta/propellerads-mcp.git
cd propellerads-mcp
pip install -e .
Configuration
Add to your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"propellerads": {
"command": "python",
"args": ["-m", "propellerads_mcp"],
"env": {
"PROPELLERADS_API_TOKEN": "your_api_token_here"
}
}
}
}
Restart Claude Desktop and you're ready to go!
Example Commands
Campaign Management
"Show me all my active campaigns sorted by ROI"
"Create a push campaign for gaming offers in Brazil with $100 daily budget"
"Pause all campaigns with negative ROI in the last 7 days"
"Clone my best performing campaign to Mexico, Colombia, and Peru"
Performance Analysis
"What's my campaign performance for the last week?"
"Compare this week's performance vs last week"
"Show me the top 10 zones by conversions for campaign 12345"
"Which creatives have CTR below 0.5%?"
Optimization
"Find all zones spending over $50 without conversions and blacklist them"
"Show me campaigns ready for scaling (ROI > 50%)"
"Find top performing zones for my dating campaigns"
Available Tools
Campaign Tools
list_campaigns- View all campaigns with filtersget_campaign_details- Get complete campaign informationcreate_campaign- Create new advertising campaignsupdate_campaign- Modify campaign settingsstart_campaigns- Activate campaignsstop_campaigns- Pause campaignsclone_campaign- Duplicate successful campaigns
Statistics Tools
get_performance_report- Detailed performance metricsget_campaign_performance- Campaign summary with insightscompare_periods- Period-over-period analysisget_zone_performance- Placement-level analyticsget_creative_performance- Creative performance breakdown
Optimization Tools
find_underperforming_zones- Find zones wasting budgetfind_top_zones- Identify best placements for whitelistingfind_scaling_opportunities- Find campaigns ready to scaleauto_blacklist_zones- Automatically blacklist bad zones
Targeting Tools
add_to_whitelist- Add zones to campaign whitelistadd_to_blacklist- Add zones to campaign blacklist
Account Tools
get_balance- Check account balanceget_available_countries- List targetable countriesget_ad_formats- List available ad formats
Security & Permissions
- API Token: Stored securely in environment variables
- Read Operations: Executed without confirmation
- Write Operations: Require explicit user confirmation
- Rate Limiting: Respects PropellerAds API limits
Use Cases
Daily Optimization Routine
1. "Show me yesterday's performance for all campaigns"
2. "Find and blacklist underperforming zones"
3. "Show me campaigns ready for scaling"
Campaign Scaling
1. "Find campaigns with ROI > 100% and at least 50 conversions"
2. "Clone top performer to similar GEOs"
3. "Increase budget by 50% for profitable campaigns"
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Support
- Issues: GitHub Issues
- Author: @jannafta
- Website: jannafta.com/ia
Keywords
propellerads mcp programmatic dsp ssp adtech adops performance-marketing igaming media-buying rtb cpm cpc cpa push-notifications popunder interstitial ai-automation claude anthropic
Made with love for the programmatic advertising community
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。