Announcing MCP support in Apigee hybrid: agentic tools that run in your own cluster

Apigee hybrid 1.17.0 introduces Model Context Protocol support for organizations that run API infrastructure in their own Kubernetes clusters, data centers, or other clouds, allowing existing OpenAPI-defined APIs to become discoverable AI-agent tools without custom MCP server code. The MCP data plane operates within the customer’s cluster, keeping request and response traffic local while periodically pulling configuration from Apigee’s control plane without requiring inbound Google Cloud connections. MCP endpoints retain Apigee security, API product-based tool authorization and quotas, governance policies, cataloging in API hub, and tool-level monitoring through API insights. The optional feature is enabled through Helm upgrades and a one-time control-plane permission for the existing apigee-watcher identity, with maintenance-window planning recommended because changes trigger staged runtime releases. Apigee also supports distributed tracing by translating W3C trace context from MCP JSON-RPC metadata into standard downstream headers, enabling end-to-end visibility across AI clients, proxies, and backend services.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.