Evolution of Agent Tooling (Tools → MCP → Skills)

#concept

Summary

Konstantin's three-generation map of how agents get capabilities: Tools (2022–2024) → MCP (late 2024–2025) → Skills (2025→). Each generation trades off developer cost, context consumption, and flexibility.

Current Understanding

Generation	What it is	Strength	Weakness
Tools	Function tagged and injected into the model call (LangChain/LlamaIndex)	Direct control	Every tool eats context; you write/adapt each yourself
MCP	Locally-deployed server exposing many tools via a standard protocol (Anthropic); marketplaces exist	Ready-made tools, plug-in	Dozens of tools per server → context blowout (>100 = chaos); network-load = security surface; needs a developer
Skills	Directory + `SKILL.md` (+ tools + data), two-stage loading	Hundreds without context blowout; author with text in any language; share via git/messenger	No standards yet for data/limits

When to use which: Skills when tasks are unknown/diverse or tool count is ~5–50; MCP when the agent is narrow, tasks are uniform, and the same small toolset applies every time. The line blurs — Claude Code converts MCP servers into skills (file laid down, functions not all injected), erasing most MCP downsides. Konstantin doesn't hate MCP; its problems are largely solved.

Evidence

Three generations, per-generation problems, skills-vs-MCP decision table, Claude-Code-turns-MCP-into-skills caveat — 2026-07-14-skills-based-on-git.
Skills as portable markdown folders across Claude/Perplexity/Gemini — 2026-07-14-gap-between-ai-users-irreversible.

Concepts: skills-as-memory, harness, context-as-scarce-resource
Tools: claude-code, hermes
Entity: konstantin

Contradictions / Uncertainty

"Everything changes every 6 months" — MCP was just ratified and A2A is already wanted; this map may shift quickly. Status: tentative.

Next Questions

Where does agent-to-agent (A2A) sit in this progression?

2.1 KiB Raw Blame History Unescape Escape