flash_us0101

How is it different from Context Hub https://github.com/andrewyng/context-hub?

CLI is great when you know what command to run. MCP is great when the agent decides what to run - it discovers tools without you scripting the interaction.

The real problem isn't MCP vs CLI, it's that MCP originally loaded every tool definition into context upfront. A typical multi-server setup (GitHub, Slack, Sentry, Grafana, Splunk) consumes ~55K tokens in definitions before Claude does any work. Tool selection accuracy also degrades past 30-50 tools.

Anthropic's Tool Search fixes this with per-tool lazy loading - tools are defined with defer_loading: true, Claude only sees a search index, and full schemas load on demand for the 3-5 tools actually needed. 85% token reduction. The original "everything upfront" design was wrong, but the protocol is catching up.

That's close to what I'm thinking about. Curious what debugger setup you're using with agents - are you giving them access via MCP or just having them run CLI commands?

Timestamps aren't the issue. The problem is the cycle itself: stop the process, add the log line, restart, wait for the right conditions to hit that code path again. For anything timing-sensitive or dependent on external state, each restart changes what you're trying to observe.

Most replies here are about writing code faster. But there's a gap nobody's talking about: AI agents are completely blind to running systems.

When you hit a runtime bug, the agent's only tool is "let me add a print statement and restart". That works for simple cases but it's the exact same log-and-restart loop we fall back to in cloud and containerized environments, just with faster typing.

Where it breaks down: timing-sensitive code, Docker services, anything where restarting changes the conditions you need to reproduce.

I've had debugging sessions where the agent burned through 10+ restart cycles on a bug that would've been obvious if it could just watch the live values.

We've given agents the ability to read and write code. We haven't given them the ability to observe running code. That's a pretty big gap.

Thanks for sharing! Was thinking of doing similar tool myself. That's great alternative to -dangerously-skip-permissions