In Part 1 of this series, we built a Quarkus-based MCP tool server and connected it to the Goose AI agent over Streamable HTTP. The moment you imagine 50 developers running Goose on their laptops, all hitting the same set of backend MCP servers, the architecture starts to crack.
In Part 1 of this series, we built a Quarkus-based MCP tool server and connected it to the Goose AI agent over Streamable HTTP.
The moment you imagine 50 developers running Goose on their laptops, all hitting the same set of backend MCP servers, the architecture starts to crack.
This article answers those questions by placing agentgateway — the Linux Foundation's open-source proxy for agentic AI traffic — between Goose clients and the Quarkus MCP microservices we built in Part 1.
The page is ready to read now. The fuller skim-friendly version will appear here automatically.
In Part 1 of this series, we built a Quarkus-based MCP tool server and connected it to the Goose AI agent over Streamable HTTP. The moment you imagine 50 developers running Goose on their laptops, all hitting the same set of backend MCP servers, the architecture starts to crack. This article answers those questions by placing agentgateway — the Linux Foundation's open-source proxy for agentic AI traffic — between Goose clients and the Quarkus MCP microservices we built in Part 1.
Which role authorized the getAuditTrail invocation?
Open the app view to save this story, compare related coverage, and continue from the same source.