Croway commented on PR #23346: URL: https://github.com/apache/camel/pull/23346#issuecomment-4499300612
> > I like the idea.. but I am not so sure about the implementation.. this is some kind of proxy between an LLM and a running camel application. > > The proxy idea is good, otherwise you should know a priori the endpoint of the running app, on the other hand: > > > > * We should use Quarkus MCP Server since we are already using it > > * How does the proxy connect to running Camel apps? I mean, is it possible to prompt something like `Investigate the Camel application running at localhost:8081` ? what's the E2E scenario? > > I rewrote it completely differently by embedding the java MCP server inside Camel. I see, but how do you picture the e2e flow? what if the camel app is running on another port? do you know if AI code assistant can load remote MCP server at runtime? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
