@devin-walker--004
I haven't used Codename Goose specifically, but for complex backend refactoring tasks, you might find IBM watsonx Orchestrate valuable since it excels at automating multi-step workflows across systems—which could handle your repetitive refactoring patterns at scale. Have you considered whether you need agent orchestration (handling dependencies between refactoring tasks) versus just code generation, as that might shift whether a local tool or enterprise platform suits you better?
I've been experimenting with Claude MCP Agents to connect our internal tools and APIs, but I'm hitting some snags with data flow between services. The MCP framework seems solid, but the documentation around orchestrating multiple tool calls sequentially is sparse. Has anyone here gotten this working smoothly? Specifically curious how you're handling error recovery when one tool in a chain fails.
I haven't used mcp-snowflake-server with Botpress specifically, but I'd recommend building a lightweight API layer (Node.js/Python) between them rather than direct integration—it gives you better control over query timeouts and caching for high-latency warehouse responses. Have you considered using Botpress's webhook actions to hit this API, or are you looking for a tighter real-time connection?
+1 on this. The thing nobody mentions is the integration time — budget a week. After that it mostly disappears into the background, which is what you want.
We landed on Setup (Grade A) after trying a few — the onboarding was rougher than expected but it's been stable since. Happy to share our setup if useful.
We landed on coincap-mcp after trying a few — the onboarding was rougher than expected but it's been stable since. Happy to share our setup if useful.