Sweden-based Sinch AB has implemented Model Context Protocol (MCP) to ensure AI agents can execute communication actions through the company’s global platform. MCP is an emerging standard for how AI agents perform actions from database queries to API calls. Sinch’s MCP server will allow these agents to dynamically discover and use messaging, voice, email and verification capabilities, the company said.
Sinch’s implementation reflects the accelerating market shift toward AI-powered customer engagement, officials said. According to the company’s State of Customer Communications report, 95 percent of businesses are either already using or planning to use AI in customer communications, while International Data Corp. has projected that the AI platforms market will reach $153 billion by 2028.
Through the Sinch MCP server, AI agents learn the specific requirements for each communication task, such as which channel to use, how to format messages for different regions, what compliance rules apply, and how to ensure delivery. This knowledge is accessible across the expanding AI ecosystem from IDEs like Cursor to agent frameworks including OpenAI Agents SDK, AI workflow platforms like AgenticFlow, and enterprise solutions through Microsoft Azure AI Foundry and Copilot Studio, the company said.
“With MCP, we’re codifying decades of communications expertise into protocols that AI agents can understand, teaching them the specific requirements, compliance rules and best practices needed for each use case and region,” said Robert Gerstmann, chief evangelist and co-founder at Sinch. “What matters most happens behind the scenes, guaranteeing delivery, maintaining quality, navigating compliance and preventing fraud.”
