Hi everyone,I'm currently trying to integrate Claude Desk with an MCp in n8n. I'm running into an issue where the MCP doesn't seem to be recognized or queried properly from Desk. I'm using Sonnet 4 (the free version), and I was wondering: is it only possible to query an MCP from Desk if you're using Sonnet 3.7 (which requires a paid plan)? Could that be why the MCP isn't being accessed correctly? Thanks in advance for any help! Emanuele

Hi everyone 👋 I'm currently working with an AI Agent in n8n and noticed something odd about the HTTP Request tool integration. 🔍 When I use a regular HTTP Request node in a workflow (see point 1 in the image), I can see and use the “Import cURL” button just fine. However, when the HTTP Request is used as a tool inside an AI Agent (point 2 in the image), the “Import cURL” button is missing from the UI. This makes it harder to quickly debug or copy the request. I’m on n8n version 1.85.4, which I believe is recent enough to include this feature. I’ve also seen in some webinars that the cURL button should be available even for HTTP tools inside agents. ➡️ Is this a known limitation or a bug?➡️ Has anyone managed to get the cURL button to show in this context? Thanks in advance! Emanuele

Hi everyone, I’ve built a workflow where, given a company’s industry code, an LLM generates a sector analysis and updates a specific field in our CRM. My problem is that there could be multiple bulk requests happening at the same time, and I want to implement a queue system to avoid hitting the LLM's token-per-minute limit. I tried using the Batch node to create a queue, which works in grouping items, but I can’t manage to enforce a fixed interval of one request per minute. Is there a reliable way to process one item from the batch every 60 seconds? Would love suggestions or patterns you've used to handle this kind of isssue with LLMs inside n8n! Thanks in advance 🙏 Emanuele