Introducing the Voucherify MCP Server

When Voucherify showed up in the loyalty space, we didn’t show up with a slide deck full of buzzwords about “unlocking ROI synergies.” We did something far less glamorous and far more useful: we built a system that helps teams run promo experiments quickly. The faster you run tests, the faster you learn, and the faster you stop wasting money on loyalty tactics that don’t work.

That’s why we built Voucherify around two principles:

• Fast integration that gets you up and running without weeks of setup.
• A simple “build → launch → learn” loop that makes it easy to run many small experiments, gather insights, and keep iterating.

Brands like Michelin, Breville, and easyJet have already ditched clunky “one size fits all” loyalty programs in favor of lightweight, targeted incentives they can spin up and shut down without blowing their budgets. That’s the kind of experimentation culture Voucherify was built to support.

But while marketing tools have marched from spreadsheets to dashboards to machine-learning-powered analytics, actually getting at the raw data is still a pain. That’s the bottleneck we’re breaking. 

Enter the Voucherify MCP Server (beta), our first step into agent-driven data interaction. It lets you query and explore your loyalty & promo data in plain language, as if you were asking a teammate to pull the numbers for you. 

See the full documentation >

What is Model Context Protocol (MCP)?

The Model Context Protocol is basically a handshake agreement between AI systems and the rest of your stack. Instead of hacking together custom connectors every time you want an LLM to talk to your data, MCP provides a standardized way to expose exactly what the AI can see and do.

It has two moving parts:

• MCP Client – the environment where the AI agent runs (for example, a code editor or chat interface).
• MCP Server (or package) – a locally hosted service that specifies which data the AI can see and which actions it can take.

Because both sides speak the same protocol, wiring things up doesn’t turn into a six-week integration death march. You spin up the server, point your AI client at it, and suddenly you can have a conversation with your data instead of writing boilerplate queries.

How does Voucherify MCP server work?

Once you’ve set up the Voucherify MCP on your local machine, you can plug AI tools directly into Voucherify. This connection lets those tools pull information about campaigns, promotion tiers, orders, products, vouchers, and more, without touching or altering your data.

Key note:

The MCP server is read-only, so you can safely explore campaign data without the risk of editing, overwriting, or deleting anything.

Getting started is simple

1. Pick your workspace: Claude Desktop, Cursor, VS Code, or another MCP client.
2. Retrieve your Voucherify API keys from the Project Settings in the Dashboard.
3. Complete the quick setup steps to install the MCP server.
4. Start querying your data in plain language.

How to use the Voucherify MCP server?

The Voucherify MCP server makes your promotion and loyalty data accessible through natural language queries, so teams can work faster without waiting on custom reports or engineering help.

Here’s what you can do with it:

• Track coupon and loyalty performance: Get instant insights into voucher usage and program engagement without requesting one-off exports.
  
  
• Access live campaign details: Pull active campaign durations, continuity, and rules straight from Voucherify or pipe them into BI tools.
  
  
• Measure performance per SKU: See how individual products contribute to campaign results, without the manual number crunching.
  
  
• Support customer service teams: Use agent-based workflows to quickly check promo code status, redemption history, and customer eligibility.
  
  
• Integrate with your wider stack: Connect Voucherify data with platforms like Salesforce Agentforce or other MCP integrations. This enables adaptive promotion management like automatically fine-tuning campaigns based on BI insights.

Voucherify MCP server prompt examples

• “Find products where attribute ‘category’ = ‘Burgers’ and price < 20.”
• “Find customer by email tom@example.com (or source_id); return id, loyalty_balance, active_vouchers.”
• “Count total of customers in segment ‘VIP-Warsaw’”
• “List active campaigns with fields id, name, type, start_date, end_date.”
• “Get voucher by code ‘BK-4829’ and show: status, redemption.count, redemption.limit, balance (if gift-card).”
• “Get campaign ‘BK-Sept-20OFF’ counters: total budget, spent budget, redemption counts, and per-customer caps.”
• “Get redemptions aggregated by day for 2025-09-01 → 2025-09-03 (timezone Europe/Warsaw).”
• “Top 10 codes by redemption count in the last 14 days; include redemption.success vs. redemption.failed.”
• “Export redemptions to CSV for 2025-09-01 to 2025-09-03 and provide a download URL.”

Best practices for using the Voucherify MCP server

From our own testing, here are some practical tips to get the most accurate and useful results out of our MCP:

1. Be specific in your queries

• Use precise date ranges (e.g., “July 2025 redemptions”) instead of vague prompts like “recent redemptions.”
• Call out exactly what you want: specific campaign names, product categories, or data types.
• Broad requests (e.g., “all campaigns in the last 3 years”) usually lead to messy results.

2. Don’t just ask

If results look off, reframe your query or try again. If the AI loops or repeats itself, redirect with a new question or start a fresh chat with a sharper prompt. 

3. Dig deeper

Once you’ve got an answer you like, ask MCP to:

• Suggest additional insights or next steps.
• Explain how it reached its conclusions (to help refine your future prompts).

4. Prioritize by impact

If you’re short on time, ask MCP to sort results by what matters most like biggest revenue lift, quickest win, or highest time savings. This helps cut through information overload.

Join Voucherify MCP Server Beta

We’re opening our MCP Server Beta to Voucherify users who want a smarter way to work with their data. The server provides read-only, conversational access to campaigns, canvases, segments, and attributes, securely and without exposing PII.

The first iteration covers the following functionalities:

• Find_customer – to display a customer’s current status and detailed information such as collected loyalty points, eligibility for rewards, and other profile data.
  
  
• List_campaigns – to retrieve a list of campaigns filtered by status, creation date, or other criteria, making it easy to view active, scheduled, or completed promotions.
  
  
• Get_campaign_summary – to display a performance snapshot of ongoing campaigns, including comparisons with past activity (e.g., previous week), allowing you to visualize trends and measure success over time.
  
  
• Get_promotion_tier – to fetch details about a promotion’s tier configuration, such as reward levels or thresholds that determine customer benefits.
  
  
• Qualifications –  to check and return a customer’s eligibility for specific campaigns, promotions, or reward rules, ensuring only qualified users receive incentives.
  
  
• Get_best_deals – to return information about better prices contextually.
  
  
• List_products – to retrieve the catalog of products, including attributes like pricing, availability, and categories, to power product selection and targeting.
  
  
• Get_voucher – to return full details of a specific voucher, such as code, status, balance, and expiration date, to support redemption or troubleshooting.

Best practices:

• Use dedicated API keys for MCP (don’t reuse existing ones).
• Scope access carefully to avoid overexposure.
• Validate critical insights before making strategic decisions.

With MCP, you get safe, AI-powered exploration of your engagement data, unlocking faster, deeper insights without custom reports.

Disclaimer

The Model Context Protocol (MCP) is a new open-source standard and may still carry potential vulnerabilities. The Voucherify MCP server setup and instructions are provided “as is,” without warranties, and use is at your own risk.

Voucherify is not liable for issues caused by incorrect setup, misuse, or security gaps related to MCP. 

If you have questions or need support, please reach out to our team, we’re here to help.

{{CTA}}

Connect your MCP client with Voucherify

Start now

{{ENDCTA}}