Visa has expanded its Intelligent Commerce program with the introduction of a Model Context Protocol (MCP) Server and a Visa Acceptance Agent Toolkit, designed to help developers and business users connect AI agents directly to Visa’s network.
The MCP Server allows developers to link AI agents and large language models with Visa Intelligent Commerce APIs, creating a standardised and secure way to integrate payments. “For AI agents and LLMs to interact with Visa’s trusted network, they need a secure, consistent way to communicate with our services,” the company said in its announcement.
According to Visa, the MCP Server eliminates the need for custom-built integrations, accelerates prototype development, and allows agents to dynamically apply Visa APIs to commerce tasks. Early adopters within Visa have already used the technology to streamline generative AI workflows.
The company also announced the pilot of the Visa Acceptance Agent Toolkit, which runs on the MCP Server. It is designed to let both developers and non-technical users complete commerce tasks in plain language without coding.
“Now available in pilot, the Visa Acceptance Agent Toolkit empowers both developers and business users to put agentic commerce into action — without writing a single line of code,” Visa noted.
Initial use cases include creating invoices and summarising transaction data through natural language commands. For example, a user could request: “Create an invoice for $100 for John Doe, due Friday,” and the agent would process the request through Visa’s Invoice API.
The Toolkit is currently available as a self-hosted package via npm for JavaScript developers, with all actions routed through the MCP Server under Visa’s security and access controls.
Visa said both the MCP Server and Toolkit remain in pilot while the company explores further B2B and B2C applications. “Trust is crucial for enabling AI commerce,” Visa stated, adding that its decades of work with machine learning and datasets position it to support secure, next-generation payments at scale.
