How to Use the ReferralCandy MCP in Claude Code
Run ReferralCandy operations and track advocate rewards directly from your terminal using Claude Code.
Works with every AI agent you already use
…and any MCP-compatible client
Connect ReferralCandy MCP to Claude Code
Create your Vinkius account to connect ReferralCandy to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.
Key Capabilities
Pipe ReferralCandy Stats to Terminal Tools
The `get_stats` tool lets Claude Code fetch raw campaign metrics and pipe them directly into command-line utilities like jq, grep, or custom shell scripts. You run quick CLI audits on your referral performance without opening a web browser or writing python scripts. For automated reporting, Claude Code queries `list_referrals_by_period` and outputs clean JSON that you redirect to local log files. This MCP server makes monitoring your ReferralCandy metrics fast and scriptable.
Script Purchase Registrations via Claude Code MCP Server
The `register_purchase` tool allows Claude Code to process referral purchases directly from server logs or database export files. You pipe a CSV of offline transactions into Claude Code, and it sequentially calls the registration API to credit the correct advocates. If you run cron jobs, Claude Code uses `check_referralcandy_status` to verify API availability before executing mass batch uploads. This terminal-first approach ensures your custom transactional integrations remain reliable and easy to debug.
Headless Referral Auditing in Claude Code
The `list_pending_rewards` tool gives Claude Code the capability to scan your account for unfulfilled advocate incentives directly from an SSH session. You ask Claude Code to filter these pending rewards and output a clean list of advocate emails that need manual payout approvals. By combining `get_referrer` and `list_invites`, Claude Code traces the complete path of any referred customer to diagnose why an invite didn't trigger a reward. This deep terminal debugging saves backend developers from digging through web dashboards.
Set up ReferralCandy MCP in Claude Code
Prerequisites
- Claude Code CLI installed (
npm install -g @anthropic-ai/claude-code) - Active Vinkius subscription with a valid endpoint token
- 1
Run the add command
Open your terminal and run the command shown on the right. Replace
[YOUR_TOKEN_HERE]with your endpoint token from cloud.vinkius.com. Use--scope userto make it available across all projects. - 2
Verify the connection
Start a Claude Code session and type
/mcpto list connected servers. You should seereferralcandy-mcpwith a green status indicator. - 3
Start using tools
Ask Claude Code something like "Check my latest ReferralCandy transactions." It will automatically discover and invoke the available ReferralCandy tools.
claude mcp add --transport http referralcandy-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
Real-time monitoring
Live
visibility into every interaction
Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.
Built-in savings
60%
lower AI costs
Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.
Single dashboard
One
place for every integration
Every tool your AI connects to, managed from a single screen. One account, complete control.
Common questions about ReferralCandy MCP in Claude Code
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the ReferralCandy MCP today
We host it, we monitor it, we maintain it. You just paste one token.