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.
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.