The agent-native loyalty reader
Connect any AI agent to your loyalty program. Sync your Rivo data — points events, redemptions, rewards, referrals, and VIP tiers — into your organization's Brain, then ask in natural language: 'which VIP tier actually repurchases?', 'what are we paying out in points versus getting back?', 'how much revenue came from referrals last quarter?'. Bounded, resumable syncs keep the picture current without re-reading everything.
How it works
From a connected loyalty program to queryable data in four steps.
Sign up and get an API key
Create a free account at gentic.co, generate an API key from your dashboard, and use it as a Bearer token to authenticate your agent.
Connect Rivo in your dashboard
Paste your Rivo REST API key once in the Gentic dashboard (Integrations → Rivo). Mint it in Rivo under Settings → Developer Toolkit → REST API Keys. The key is encrypted at rest and checked against Rivo on connect, and we read back which store it belongs to automatically — there's nothing else to choose. The Loyalty server picks the connection up on its own; your agent never handles the credential.
Add the MCP server to your agent
Drop https://mcp.gentic.co/loyalty into Claude Code, Claude Web, OpenClaw, Claude Cowork, ChatGPT, n8n, or any MCP-compatible client. Pass your Gentic API key as a Bearer token — or connect via OAuth on clients that support it.
Sync, then ask anything
Run rivo_sync to pull your loyalty data into your Brain — bounded and resumable, so you can page through it a chunk at a time. Then ask your agent in plain language about redemption trends, points economics, or referral performance, and it queries the synced tables.
Available tools
2 tools your AI agent can call through the Model Context Protocol.
rivo_connection_status
Check whether the calling organization has connected Rivo (the rivo.io loyalty app).
rivo_sync
Sync loyalty data from Rivo (rivo.io) into this organization's data backend — READ-ONLY, verbatim, one BOUNDED chunk per call.
Connect in seconds
Sign up, connect Rivo in your dashboard, grab your API key, and add the MCP server to your agent. Works with Claude Code, Claude Web, OpenClaw, Claude Cowork, ChatGPT, n8n, and any MCP client.
claude mcp add gentic-loyalty \
--transport http \
https://mcp.gentic.co/loyalty \
--header "Authorization: Bearer YOUR_API_KEY"You can also connect via OAuth — just add gentic-loyalty as a connector in Claude or ChatGPT settings. No API key needed; authentication is handled automatically.
Install the Gentic agent skill to teach your agent the optimal workflow so it gets the best results automatically.
npx skills add gentic-co/agent-skillsWorks with Claude Code, Cursor, Copilot, and 40+ other agents.
Free to sync, pay only for analysis
Syncing your Rivo loyalty data into Gentic and checking the connection are both free — you only pay for the analytics you run over it.
| Tool | Cost |
|---|---|
| rivo_connection_status | Free |
| rivo_sync | Free |
Pricing is pulled live from the Gentic MCP manifest so it always matches what you'll actually be charged.
Why agent-native loyalty?
Loyalty dashboards report on the loyalty program. The question worth answering is almost never inside it — it's whether the program changes what customers do, which means reading it next to your orders, subscriptions, and surveys.
No UI to learn
Your AI agent is the interface. Ask which tier actually repurchases, or what a points liability is costing you — in natural language, no filters to click, no exports.
It lands in YOUR warehouse
This is the difference from a loyalty vendor's own read-only integration. Your data lands in your organization's Brain next to your subscription, order, and survey tables — so you can join across them, keep the history, and query it long after any single vendor relationship.
Portable
Works with any MCP-compatible client — Claude Web, Claude Code, OpenClaw, ChatGPT, n8n, and more. Switch clients without changing a thing.
Free to sync
No monthly seats or platform fees. Syncing your Rivo data and checking the connection are free — you only pay for the analytics you run over it (e.g. query_data on the Gentic Data MCP).