Viavi Solutions has embraced the model context protocol (MCP) standard, adding a server framework to its Nitro AI platform to allow engineers to securely run tests using natural-language prompts.
Where traditional automation requires manual script configuration across testing tools, Viavi is tapping the Anthropic-developed MCP standard to provide private connections between infrastructure testing tools and AI clients. The server framework integrates with the firm’s wider testing offerings, including TestCenter for network performance and CyberFlood for security and application assurance.
Viavi’s MCP addition includes autonomous error correction loops that detect and self-correct test tool misconfigurations, though a human engineer would review checkpoints at critical testing points. Testing functions act as standardized tools that AI agents can execute through conversational commands, a move Viavi says can greatly reduce reliance on scripts and APIs.
“Network infrastructure is evolving faster than the supply of specialists who can validate it, so validation has to become AI-native,” Sashi Jeyaretnam, Viavi’s senior director for security product management, explained. “The MCP server framework helps close that gap by reducing time-to-test and operational cost while making complex validation accessible to a broader range of engineers.”
Viavi’s MCP support comes as the testing giant continues to double down on AI tools to aid user performance assurance efforts. Earlier examples include adding AI to its line of fiber monitoring solutions to analyze data from fiber links during testing. It’s also lending its expertise to future AI-augmented networks as part of a Nokia lab project.