MCP

A practitioner's end-to-end tutorial on MCP — the three-layer agent stack, progressive discovery, programmatic tool calling, and hands-on labs from beginner to advanced. Useful if you want to go deeper than the official docs.

The Honeycomb team shares their second round of hard-won patterns for running MCP and canvas-based agent workflows in real observability work. Rare glimpse of the integration grief no vendor doc admits to.

Major host applications released MCP v2.1 support this week. Linux Foundation's Agentic AI Foundation now governs MCP and A2A. Connect agents to external tools without custom integration code.

Technical examination of MCP v2.1 architecture, messaging patterns, and implementation. Shows how the protocol enables standardized tool integration across all major AI platforms.

A practitioner breakdown of MCP vs CLI trade-offs, arguing MCP remains the right choice for enterprise agent adoption despite valid developer complaints about complexity and auth.

Eric Holmes makes a compelling case that the Model Context Protocol adds unnecessary complexity when LLMs already excel at using command-line tools. He argues CLIs offer superior debuggability, composability, authentication, and reliability — and that MCP solves a problem agents don't actually have. A sharp contrarian take that's generated heated discussion in developer circles.