Welcome back to Behind the Build;our interview series spotlighting the product leaders behind Nuvei’s most impactful innovations. Each edition takes you inside the strategy, technology, and merchant impact of what we’re building and why.
In this edition, Nuvei's Head of Product Marketing, Francesca Bonnett, sits down with Hilla Peled, SVP AI & Data Science, and Dror Ben Eliyahu, Director of Solutions & Implementation, to explore Nuvei’s first Agent for Integrations built on Model Context Protocol (MCP).
It’s an important step forward: not just in AI and payments, but in how merchants and developers work with Nuvei. Integration is where every merchant journey begins - and by making it faster, smarter, and more reliable, we’re reshaping the foundation of merchant experience.
Introductions
Francesca: Hilla, Dror; let’s start with your roles at Nuvei. How do you fit into this story and the release of MCP?
Hilla: I lead our AI and data science teams. My focus is identifying opportunities to transform Nuvei’s products with AI, making them more efficient, more sophisticated, and ultimately more valuable to merchants. In the context of Model Context Protocol, we saw the potential to change not just how systems work, but how people interact with them.
Dror: I oversee solutions and integrations for the EMEA region through onboarding, technical support, and success management. Integrations are at the heart of what Nuvei does. They’re the bridge between product capabilities and merchant experience, I’d say MCP essentially redefines that bridge.
What is Model Context Protocol (MCP)?
Francesca: For those unfamiliar, what is Model Context Protocol (MCP), and why is it important for merchants?
Hilla: I think of MCP as a universal connector, almost like a USB-C for AI, APIs, and databases. It’s allowing AI agents -like our new Agentfor Integrations - to access the right context instantly and interact with your systems reliably.
For merchants, this release means integration will become faster, cleaner, and less dependent on manual intervention. Instead of weeks of effort, setup can be done in hours, through clean, straightforward conversations with a chatbot.
It’s actually not just about speed either, MCP enables systems to “talk” to each other too, reducing:
- Repetitive tasks like searching documentation, or writing commonly-used code.
- Manual errors, particularly common when coding.
We actually measured up to a 40% reduction in setup errors during testing. That’s where the merchant benefit is clearest, because MCP frees up ateam's time to focus on higher-value work.
What problems does MCP solve?
Francesca: What problem were we trying to solve when we built Nuvei’s first MCP agent?
Dror: Integration is always the first step in a merchant’s payments journey. Historically, it’s also one of the most complex and time-consuming. By bringing an MCP agent into play, we’re cutting down integration timelines dramatically.
Then there’s the ease of upgrading for existing merchants, too. They can:
- Add features like payment methods
- Troubleshoot issues like incorrect code without escalation
- Implement new product enhancements like subcriptions
All of these actions can be completed, without needing to rely on manual assistance from our teams.
It gives them more autonomy and accelerates time-to-value. Modern payments are all about integration, and the first part of offering something truly agentic is enabling two systems to effectively talk to each other.
Hilla: Exactly. And it’s worth saying we didn’t rush to build MCP, despite there being other providers announcing similar products to the market. We built MCP deliberately and tested rigorously, both in-house and in beta.
- The goal was to launch an agent that can be trusted from day one, offers true transparency and 'explain-ability'.
- When interacting with an AI agent, it only takes one erroneous response, hallucination or logical error to erode user confidence in the tool.
- Therefore, the team took their time and built something merchants and developers can rely on from day one.
With AI, user trust is everything. It’s tough to earn, easy to lose, and even harder to win back.
Hilla Peled, SVP AI & Data Science
How does it MCP work?
Francesca: Can you walk us through what an integration might look like with MCP in practice?
Hilla: Ok, so if we imagine a merchant launching a new eCommerce site, for example. With MCP they log into their portal and simply ask their AI assistant to “integrate with Nuvei.”
From there:
- The agent connects to our documentation via MCP
- Generates the necessary code
- Asks clarifying questions
- Resolves any errors
- Completes the setup
Dror: That’s exactly how it works, especially for the simpler use cases. For more complex integrations - let’s say, involving tokenization, multiple payment methods, or detailed reconciliation flows - MCP still accelerates the process significantly.
- The underlying intention for MCP's Integration Agent is to help merchants move faster without sacrificing reliability.
- This rule should apply no matter how simple or complex their needs, or their coding credentials.
- Someone with no developer experience can now generate working code and manage a live integration to Nuvei.
Product build challenges
Francesca: So, Hilla, what do you think was the most challenging part of the build for your team?
Hilla: Honestly, the challenge was that MCP, as an agentic product, is still a new, developing technology. We had to understand it deeply, adapt it to our needs, and ensure it could meet security, compliance and trust standards merchants expect from Nuvei.
That meant multiple close collaborations across teams, including:
- AI and Data Science
- DevOps
- Security
- Integrations
We even built new cloud environments to support the agent, so, it was a company-wide effort.
Fitting into Nuvei's product strategy
Francesca: And for you, Dror, how do you see MCP fitting into Nuvei’s broader product evolution?
Dror: For me, this is the foundation of Nuvei’s progress toward offering agentic commerce. Integration is where systems first need to talk to each other and now, with MCP, they can. From here, the possibilities expand dramatically: agent-to-agent checkout, automated reporting, troubleshooting, even treasury optimization.
- This launch sets the stage for Nuvei's agentic commerce proposition.
- Over time, we’ll see more agents emerge that support payments, fraud, reporting, and beyond.
- The vision for Nuvei is an ecosystem where merchants, developers, and Nuvei interact more fluidly through AI.
Looking ahead
Francesca: Looking ahead, what excites you most about the future of agents in commerce?
Hilla: For me, it’s the speed of change. We’re at the very beginning of agentic commerce, and the possibilities are huge. What excites me is giving merchants tools that let them move faster, radically reduces errors, and focus on growth rather than complexity.
FAQs
Q. What is Model Context Protocol (MCP)?
MCP is an open standard that allows AI agents to connect with APIs, databases, and documentation seamlessly. It helps systems “talk” to each other, making automation and integration faster and more reliable.
Q. What does Nuvei’s Agent for Integrations do?
It’s an AI-powered agent built on MCP that automates the merchant integration process. It can generate code, answer setup questions, resolve errors, and complete integrations — often in just hours instead of weeks.
Q. Why is this important for merchants?
Because integrations are the first step in accepting payments. Faster, smarter integrations mean merchants can go live sooner, add new features quickly, and spend less time troubleshooting. In early testing, Nuvei’s MCP agent reduced integration errors by over 40%, helping merchants onboard more smoothly and start processing revenue faster.
Q. How does it improve developer workflows?
Developers can interact with the agent directly through AI tools, cutting down repetitive tasks. The agent accesses Nuvei’s documentation automatically and helps generate or adjust integration code in real time — improving both speed and accuracy.
Q. Is MCP secure and compliant?
Yes. Nuvei’s implementation of MCP meets strict compliance, security, and trust standards. The AI agent runs within secure cloud environments designed to protect merchant data and transactions.
Q. What’s next for AI agents at Nuvei?
This is just the beginning. Nuvei plans to expand MCP-powered agents into other areas like payments, fraud detection, and reporting — creating an intelligent ecosystem that helps merchants operate and innovate faster.
Want to learn more?
Nuvei’s first Agent for Integrations, powered by Model Context Protocol, is live and helping merchants integrate faster, reduce errors, and unlock new revenue opportunities. Contact us to learn more or reach out to your Nuvei account team if you're an existing customer.
.svg)
