"Buoyant, the company behind the open-source Linkerd service mesh, announced that Linkerd now supports the Model Context Protocol (MCP), making it the first service mesh to natively manage, secure, and observe agentic AI traffic in Kubernetes environments. The move is designed to accelerate enterprise AI adoption by offering a stable, secure, and fully observable runtime for AI-driven workflows, which behave differently from traditional API-based applications."
"The announcement comes as enterprises increasingly integrate AI agents that rely on MCP, a protocol enabling models to access external tools, data sources, and context through persistent, long-lived sessions. Unlike conventional request-response APIs, MCP-driven agentic workloads are unpredictable, stateful, and capable of generating intense resource spikes, creating challenges for organizations lacking visibility or security controls tailored to this new traffic pattern."
"Linkerd's upcoming MCP support brings core mesh capabilities, including visibility, access control, and traffic shaping, to agentic AI workloads without requiring additional tools or architectural changes. Enterprises will gain metrics on prompt usage, latencies, failure rates, and resource consumption, along with zero-trust access control for all MCP calls based on cryptographic workload identities. By layering these capabilities into the mesh itself, Buoyant positions Linkerd as a unified control plane for both traditional microservice traffic and emerging AI agent communication."
Linkerd gains native support for the Model Context Protocol (MCP), enabling the service mesh to manage agentic AI traffic in Kubernetes. MCP enables models to access external tools, data, and persistent context through long-lived sessions, producing unpredictable, stateful workloads and resource spikes. Linkerd extends visibility, access control, and traffic shaping to MCP calls without extra tools or architectural changes. Enterprises receive metrics on prompt usage, latencies, failure rates, and resource consumption, and zero-trust access control based on cryptographic workload identities. The integration creates a unified control plane for traditional microservices and emerging AI agent communications, aiming to improve security and reliability.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]