Slack’s API returned 200 OK but silently dropped my Work Objects. Two gotchas cost me hours: wrong metadata structure and a missing alt_text field. Here’s the debugging story and the channel-specific embedded resources pattern that emerged.
Manual tests aren’t about who executes them. Using Playwright MCP with Claude Code, I let my coding agent run verification scripts and catch its own regressions during code review.
OpenAI’s ChatKit has a Python SDK. I’m using Rails. Here’s how I bridged MCP tool results to ChatKit widgets, with architecture decisions, extraction logic, and lessons from letting AI agents write most of the code.
I wanted MCP auth to feel invisible. The dream was simple. User opens the app, starts chatting with the LLM. At some point they ask for something that needs an external tool. “What’s on my calendar this week?” The LLM realizes it needs Google Calendar access, prompts the user for permission right there, they approve, and the tool runs. Contextual. Just-in-time. No setup screens. This is how permissions should work. Ask for what you need, when you need it, and not a moment before. ...
When I started building Agentify, I took the straightforward path: hardcode the tool integrations directly into my Rails application. Need weather data? Write a method that calls the weather API. Need to search knowledge bases? Build it into the agent logic. It worked, but it wasn’t sustainable. Then the Model Context Protocol (MCP) standard emerged, promising a way to standardize tool interactions between AI agents and external services. Instead of building every integration myself, I could tap into a growing ecosystem of MCP servers. The question was: how do you actually implement this in a real Rails application? ...