mcp-server-design
MCP Server Design
Overview
This skill provides best practices for designing MCP (Model Context Protocol) servers that work effectively with LLM agents. The key insight: design for agents, not automation. LLMs are human-like thinkers, not API consumers.
Core Philosophy
Design for Agents, Not Automation
Traditional API design optimizes for programmatic access with granular endpoints. MCP tool design should optimize for how LLMs think and reason:
- LLMs are human-like thinkers: They understand intent, context, and purpose
- Tools should be tasks, not endpoints: Shape tools around what users want to accomplish
- Reduce cognitive load: Fewer, more purposeful tools beat many granular ones
The Three Pillars
More from xmcp-dev/skills
create-tool
Create a new xmcp tool with schema, metadata, and handler. Use when the user wants to add a new tool to their xmcp project.
35prompt-design
Design MCP prompts to expose reusable prompt templates. Use when creating parameterized prompts in xmcp.
30widget-design
Best practices for designing UI widgets in xmcp. Use when creating interactive widgets for GPT Apps or MCP Apps, choosing between React components and template literals, designing widget layouts, handling state and data fetching, or troubleshooting widget rendering issues.
30resource-design
Design MCP resources to expose content for LLM consumption. Use when creating static or dynamic resources in xmcp.
29