What if you don't need MCP at all?

kept by eddie nov 19, 25

Many developers argue that CLI tools and direct API calls are simpler and more reliable than MCP for hooking LLMs to external systems.

What we’ve learned building cloud agents
Cursor's cloud agents perform best when given full development environments, durable execution via Temporal, and a harness that shifts control to the agent.
also on GitHub CLI, Cursor, #ai-coding, #developer-tools
Stacked pull requests are now in public preview - GitHub Changelog
GitHub introduces stacked pull requests in public preview, allowing developers to break large changes into reviewable layers and merge them with a single click via the gh‑stack CLI extension.
also on GitHub CLI, #cli, #developer-tools
Security boundaries in agentic architectures - Vercel
Vercel recommends separating agent harness from generated code execution in isolated sandboxes with secret injection to prevent prompt injection and credential theft in agentic architectures.
also on #software-architecture, Cursor, Claude Code, #developer-tools
Why AI Swarms Cannot Build Architecture | An analysis of the structural limitations preventing AI agent swarms from producing coherent software architecture
AI agent swarms cannot produce coherent software architecture because architecture requires global invariants, temporal persistence, and enforcement authority—properties that swarms structurally lack.
also on #software-architecture, Cursor, #ai-coding