Kickbacks MCP Server
MCP server for Kickbacks.ai that pays developers ad revenue from AI coding agent spinners. Provides tools to check balance, earnings, status, ad history, and toggle ads.
README
Kickbacks.ai MCP Server
Earn ad revenue from AI coding agent spinners — MCP server for Kickbacks.ai that exposes tools to check balance, earnings, status, ad history, and enable/disable ads.
What is Kickbacks.ai?
Kickbacks.ai pays developers 50% of ad revenue from ads shown in AI coding agent spinners (Claude Code, Codex). While your agent "thinks", its spinner shows sponsored lines instead of generic verbs like "Discombobulating...".
| Platform | Status |
|---|---|
| VS Code Extension (Claude Code) | ✅ Primary |
| VS Code Extension (Codex) | ⚠️ Temp disabled |
| Terminal CLI (Claude Code 2.1.143+) | ✅ Works |
Quick Start
1. Get API Credentials
Email support@kickbacks.ai for partner API access.
2. Install & Configure
# Install via uvx (recommended)
uvx kickbacks-mcp
# Or install locally
pip install kickbacks-mcp
# or
pip install -e .
3. Set Environment Variables
export KICKBACKS_API_KEY=your_api_key_here
export KICKBACKS_USER_ID=your_user_id_here # optional
4. Add to Hermes Agent Config
# ~/.hermes/config.yaml
mcp_servers:
kickbacks:
command: "uvx"
args: ["kickbacks-mcp"]
env:
KICKBACKS_API_KEY: "your_key"
5. Use in Any MCP-Compatible Agent
# Check balance
> kickbacks_balance
# See earnings breakdown
> kickbacks_earnings
# Check status & caps
> kickbacks_status
# View ad history
> kickbacks_ads_history
# Enable/disable ads
> kickbacks_set_enabled enabled=true
Available Tools
| Tool | Description |
|---|---|
kickbacks_balance |
Current balance (total earnings) |
kickbacks_earnings |
Breakdown: today/week/month/total |
kickbacks_status |
Connection state, caps, session stats |
kickbacks_ads_history |
Impression/click log with pagination |
kickbacks_set_enabled |
Enable/disable ads |
kickbacks_config |
Check configuration status |
Example Outputs
> kickbacks_earnings
Earnings Breakdown:
Today: $0.42
This Week: $7.11
This Month: $42.50
Total: $156.78
Currency: USD
> kickbacks_status
Connected: ✅ | Authenticated: ✅ | Enabled: ✅ | Last sync: 2026-06-13T21:32:31 | Session: 23 impressions, 2 clicks
> kickbacks_ads_history
Ad History (showing 2 of 2):
👁 [2026-06-13T21:32:31] Ramp - save time and money (spinner) - $0.0010
👆 [2026-06-13T21:32:31] Bitcoin Devs Takeover Toronto (statusbar) - $0.0500
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
KICKBACKS_API_KEY |
Yes | API key from Kickbacks.ai |
KICKBACKS_USER_ID |
No | Your Kickbacks user ID |
KICKBACKS_API_BASE |
No | Custom API base URL (default: https://api.kickbacks.ai/v1) |
Hermes Agent Config
mcp_servers:
kickbacks:
command: "uvx"
args: ["kickbacks-mcp"]
env:
KICKBACKS_API_KEY: "ghp_xxx..."
KICKBACKS_USER_ID: "user_123"
timeout: 60
Claude Desktop Config
{
"mcpServers": {
"kickbacks": {
"command": "uvx",
"args": ["kickbacks-mcp"],
"env": {
"KICKBACKS_API_KEY": "your_key"
}
}
}
}
Development
Local Development
# Clone
git clone https://github.com/msgok/kickbacks-mcp
cd kickbacks-mcp
# Install in dev mode
pip install -e ".[dev]"
# Run directly
python -m kickbacks_mcp.server
# Run tests
pytest
Project Structure
kickbacks_mcp/
├── __init__.py # Package init
├── client.py # Kickbacks API client
├── server.py # MCP server with tools
├── pyproject.toml # Project config
└── README.md # This file
Adding Real API Support
When Kickbacks provides API access:
- Edit
client.py→ replace_mock_response()with real HTTP calls - Update data models if API differs
- Test with
pytest tests/
Publishing to PyPI
# Build
pip install build
python -m build
# Publish
pip install twine
twine upload dist/*
License
MIT License - see LICENSE for details.
Support
- Kickbacks API Access: support@kickbacks.ai
- Issues: GitHub Issues
- Kickbacks Website: https://kickbacks.ai
Built for the Hermes Agent ecosystem. Works with any MCP-compatible agent.
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。