Buoyant has unveiled upcoming support for the Model Context Protocol (MCP) in Linkerd, extending its core service-mesh capabilities and aiming to help enterprises accelerate AI adoption through a safe, reliable, and observable foundation for MCP traffic in Kubernetes environments.
"Enterprises are eager to innovate with AI, but they can't do so at the expense of their security posture and application reliability," said William Morgan, CEO of Buoyant. "Linkerd solves this problem by extending its proven capabilities to MCP traffic. We're not just enabling AI adoption, we're giving organisations the tools to accelerate their usage with confidence."
MCP Support for Linkerd
The MCP support allows Linkerd to provide the following:
- Observability of MCP traffic with metrics on resource, tool, and prompt usage, including failure rates, latencies, and volume of data transmitted.
- Security for MCP traffic through fine-grained authorisation policies for all MCP calls, using Linkerd's existing zero-trust framework built on cryptographic workload identity.
"The security concerns around MCP were initially a big factor as we started considering rolling out AI more broadly across the organisation," said Blake Romano, senior engineer at Imagine Learning. "Because we already use and trust Linkerd's enterprise capabilities, especially its strong security posture and built-in observability, it removes a major barrier to adoption. Having clear visibility into our MCP communication will give us the confidence to innovate faster, safer, and more reliably."
