Pagos Unlocks Conversational AI for Payments Data Analysis

LOS ANGELES, CA – February 17, 2026 – In a move set to redefine how businesses interact with their financial data, AI-powered payments intelligence company Pagos today announced a significant expansion of its Model Context Protocol (MCP) Server. The new capability allows merchants to query their own complex, harmonized payments data directly through popular conversational AI agents like Claude, ChatGPT, and Gemini, effectively placing a data analyst inside every chat window.

This development transforms payments analysis from a task requiring deep dives into complex dashboards into a simple, natural language conversation. For the first time, payment professionals can ask intricate questions such as, “What were the top five decline codes by transaction volume last Tuesday?” or “Show me the approval rate trend for Visa cards issued in Germany this quarter,” and receive verified, immediate answers. The launch builds on a June 2025 initiative where Pagos open-sourced an MCP server for real-time BIN-level data, now extending this conversational access to a merchant's entire trove of aggregated transaction data.

From Dashboards to Dialogue

The traditional method of payment analysis has long involved navigating multiple processor portals, exporting raw data into spreadsheets, and manually piecing together a coherent picture of performance. This process is often slow, cumbersome, and requires specialized analytical skills. Pagos aims to eliminate this friction entirely.

“Payments teams are done spending hours digging through raw payments data. They need instant & actionable insights based on verified and reliable data,” said Pagos’ CPO and Co-Founder, Albert Drouart, in a statement. The company's core strength has always been aggregating and harmonizing data from disparate sources into a single, reliable stream. “Our competitive advantage has always been payments data aggregation and harmonization—the Pagos MCP Server gives teams conversational access to that verified, consolidated, and enriched data in whatever AI workflow they're already using,” Drouart added.

This shift from graphical user interfaces to conversational ones represents a fundamental change in business intelligence. Instead of hunting for data points, users can now engage in a dialogue, asking follow-up questions and exploring data dynamically. This capability, previously available to Pagos customers for nearly two years via an internal chatbot, is now being externalized to the AI tools where many professionals are already spending their time.

Addressing the 'Do More with Less' Mandate

The announcement comes as payments teams globally face a confluence of pressures: operating with leaner headcounts, facing higher expectations for performance optimization, and grappling with the sudden dominance of AI as a primary business tool. Pagos’s new offering is squarely aimed at addressing this “do more with less” reality.

By providing instant expertise through AI, the MCP Server empowers smaller teams to perform high-level analysis that once required dedicated data analysts or expensive consultants. It democratizes access to critical insights, allowing operations managers, finance professionals, and even executives to self-serve complex data queries without needing to understand the underlying technical complexities or data structures.

“We're a Payments Intelligence company,” stated Klas Bäck, CEO and Co-founder of Pagos. “The days of flying blind without payments data visibility are done. Payment operators want answers now, and they want them in their existing AI workflows.” This focus on embedding intelligence into existing processes is key, reducing the need for context switching and accelerating the cycle from data to decision to action.

Under the Hood: Harmonizing Data for AI

The magic behind this conversational interface lies in two key areas: sophisticated data engineering and a commitment to open standards. First, Pagos leverages its powerful data platform to connect to a merchant’s various payment processors and services via no-code integrations. It then normalizes inconsistent data fields—such as decline reason codes or issuer names, which vary wildly between processors—into a single, unified data stream.

This harmonized data is further enriched using the company’s extensive BIN Database, adding valuable context like the issuing bank, card product type, and alternative routing options to each transaction. This deep, contextualized dataset becomes the “verified and reliable” foundation that the AI models query.

Second, the system is built upon the Model Context Protocol (MCP), an emerging open standard designed to be a universal connector—a sort of “USB-C port for AI”—between Large Language Models and external data sources. The MCP’s client-host-server architecture is designed with security at its core, creating isolated, secure channels for data exchange. This ensures that when a merchant queries their data via a third-party AI like ChatGPT, the data remains private and is not shared across Pagos customers or used to train the public model. Pagos provides the verified data context, but the merchant remains in full control of how it is used within their own AI environment.

Navigating a New Protocol Landscape

Pagos is not alone in recognizing the potential of connecting AI to external systems. The MCP standard is also being adopted by other major financial players like Mastercard and Mercado Pago for use cases such as API documentation queries. However, the broader landscape is becoming crowded with competing standards for “agentic AI,” where autonomous agents can perform actions like completing purchases.

Protocols such as the Agentic Commerce Protocol (ACP) from OpenAI and Stripe, and Google’s Agent Payment Protocol (AP2), are focused on enabling AI to initiate transactions. In this emerging “protocol problem,” Pagos is carving out a distinct niche. Its focus is not on enabling AI to spend money, but on empowering businesses to intelligently analyze the flow of money they have already processed. By remaining processor-agnostic and concentrating on harmonizing post-transaction data, Pagos provides a universal intelligence layer that can work across any payment stack.

This strategic positioning allows merchants to leverage the power of conversational AI for analysis without being locked into a specific payment ecosystem. For existing Pagos customers, the path to adoption is straightforward: they can add the MCP Server via their AI client’s connector settings and begin querying their data immediately. This seamless integration from the Pagos platform into a broader AI workflow fulfills the company's vision of providing payments intelligence that merchants can control and embed directly into their daily operations, transforming data from a passive resource into an active, conversational partner.