How to Use the Genius Referrals MCP in Claude Code

Q: How do I connect Genius Referrals to the Claude Code CLI?

Run claude mcp add --transport http genius-referrals -- . After that, you can use any of the server's tools, like listreferralcampaigns, directly from your terminal. Use claude mcp list to confirm it's connected.

Q: How can I check my top performers from the terminal using Genius Referrals and Claude Code?

Just run claude mcp call listtopperformers. The command will output a JSON array of your best-performing advocates, which you can then pipe to tools like jq for filtering or counting.

Q: How is my Genius Referrals data handled by Claude Code?

Data, like referral events from listtrackedreferrals, is streamed directly to stdout in your terminal. The server itself is ephemeral. It's up to you to handle that data stream securely within your scripts and avoid logging sensitive information in your CI/CD runners.

Run your Genius Referrals program from the command line. Perfect for CI/CD, cron jobs, and custom scripts with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Genius Referrals MCP to Claude Code

Create your Vinkius account to connect Genius Referrals to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Genius Referrals with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Payouts in CI/CD

This MCP server is built for headless automation. You can create a script that runs on a schedule, calls `list_payout_requests`, and pipes the JSON output to another tool for processing. It’s a solid way to build a custom approval workflow. For example, a GitHub Action could trigger on a schedule, use Claude Code to fetch pending payouts, and create a GitHub issue for your finance team to review. All without manual intervention.

Manage Advocates via Shell Scripts

Forget web interfaces for simple tasks. From your terminal, you can run `claude mcp call register_advocate ...` to add a new person to your program. It's fast and scriptable. This is also great for reporting. Pipe the output of `list_top_performers` or `list_program_advocates` directly to `jq` to filter and format the data exactly how you need it for a daily report.

Log Conversions from Anywhere

The `log_referral_conversion` tool lets you attribute new signups or sales from any system that can run a shell command. You can call it from a webhook handler in your backend service or a simple cron job that processes a queue. Because it's just a CLI command, integration is simple. There's no SDK to install. If your system can trigger a script, it can talk to your Genius Referrals account through this MCP server.

Setup guide

Set up Genius Referrals 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 user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see genius-referrals-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Genius Referrals transactions." It will automatically discover and invoke the available Genius Referrals tools.

Terminal

claude mcp add --transport http genius-referrals-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Genius Referrals MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "genius-referrals-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Genius Referrals. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Genius Referrals now

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 Genius Referrals MCP in Claude Code

Run `claude mcp add --transport http genius-referrals -- `. After that, you can use any of the server's tools, like `list_referral_campaigns`, directly from your terminal. Use `claude mcp list` to confirm it's connected.

Yes. You'd set up Claude Code in your workflow, connect to the Genius Referrals MCP server, and then you can call tools like `log_referral_conversion` as a step in your CI/CD pipeline.

Just run `claude mcp call list_top_performers`. The command will output a JSON array of your best-performing advocates, which you can then pipe to tools like `jq` for filtering or counting.

Combine Claude Code commands in a standard shell script. You can fetch a list of advocates with `list_program_advocates`, loop through them, and call `get_advocate_details` for each one to create a custom report.

Data, like referral events from `list_tracked_referrals`, is streamed directly to stdout in your terminal. The server itself is ephemeral. It's up to you to handle that data stream securely within your scripts and avoid logging sensitive information in your CI/CD runners.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript