mcp
10 essays on this topic.
- I Built 200 CLIs for My AI. Here's What Actually Matters.
A Chinese article argues CLI is becoming the AI plugin format. I've been living this for months with 442 tools. The article is right about CLI. It's wrong about what makes CLI work.
- The reversible direction
When choosing CLI vs MCP, pick the one you can undo. CLI wraps into MCP cheaply. MCP does not unwrap.
- CLI, MCP, or code mode: the answer depends on who's running the sandbox
Willison says CLIs beat MCP. Cloudflare says server-side code mode beats both. They're both right, because they're answering different questions.
- Skills as Prototype, MCP as Production
Skills and MCP servers aren't competitors. They're different stages of the same lifecycle. Build the procedure as a skill first. Graduate the tool parts to MCP when they stabilize.
- Progressive Disclosure for AI Agents
Search returns summaries. Get returns detail. The model decides what to expand. 75% context savings.
- The Integration Layer Is the Moat
MCP decouples the tool from the model. Once that happens, the durable asset isn't the model — it's which systems you've exposed.
- Progressive disclosure in MCP tools
When building MCP servers, search should return scannable summaries — not full content. Let the model decide what to read.
- What MCP Actually Changes for Enterprise AI
Not better function calling — decoupling. When tools expose MCP servers, any agent can compose any system freely. The heterogeneity problem becomes a configuration problem.
- Skills as Files
The simplest agent architecture might already be the right one: give the agent a file explaining how to do something, and let it read when needed.
- Why Every Tool Now Needs Two Faces - CLI for Humans, MCP for AI
We're building parallel interfaces for the same functionality because humans and AI agents parse the world through fundamentally different grammars. The future isn't human OR machine interfaces - it's both, simultaneously.