Architecture decision

MCP vs Agent Skills

Does the agent need new knowledge and procedure, or access to an external capability?

Get the short answerReview evidence

The short answer

Use a Skill when the missing piece is know-how. Use MCP when the agent needs live data or actions. Combine them when a procedure should teach the agent how to use a specific server safely.

Choose

Tools and MCP

Typed tools connect an agent to actions and data. The Model Context Protocol standardizes how compatible clients discover and invoke those capabilities.

  • The task requires current external data or a real side effect.
  • Typed schemas, authentication, and server errors define the boundary.
  • The capability should be shared across compatible clients.
Open the Tools and MCP guide

Choose

Agent Skills

Discoverable, reusable packages of instructions and resources that teach an agent a specialized workflow without loading the whole procedure into every session.

  • The agent already has the required tools but needs a repeatable method.
  • Templates, references, scripts, or evaluation checks belong with the workflow.
  • The procedure should remain portable without operating a service.
Open the Agent Skills guide
Use both

How the layers combine

  1. 01

    Expose narrow, well-described tools through MCP.

  2. 02

    Package the higher-level operating procedure and safety checks as a Skill.

  3. 03

    Test the Skill against supported server versions and failure modes.

Decision review

Questions to answer before implementation

  • Is the missing capability knowledge, data, or action?
  • Can the task work offline from static references?
  • Are tool inputs and side effects explicit?
  • Does the Skill pin or verify server assumptions?
  • Can failures be diagnosed at the correct layer?

Evidence ledger

Primary documentation for both sides

Reviewed July 26, 2026. Use the provider documentation for current configuration and security behavior.

MCP specification

Model Context Protocol

The official protocol model, lifecycle, capabilities, and security guidance.

Connect Codex to MCP servers

OpenAI

Current Codex MCP configuration and client behavior.

Agent Skills specification

Agent Skills

The open SKILL.md package format and progressive-disclosure model.

Build skills for ChatGPT and Codex

OpenAI

Current OpenAI Skill structure, discovery, and authoring guidance.

Extend Claude with skills

Anthropic

Claude Code Skill discovery, configuration, supporting files, and invocation behavior.