Skip to content
Back to skills

Mcp Builder

ASecurity

Designs and builds high-quality, agent-ergonomic Model Context Protocol (MCP) servers and tools following Anthropic official patterns.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 18, 2026
ai-agentsgo

Works with

  • mcp

Security analysis

A100/100

Scanned November 18, 2026

npx -y skills add Binbin-miao/workbuddy-expert-team --skill mcp-builder --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mcp Builder?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Mcp Builder
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/binbin-miao-mcp-builder/badge)](https://www.skillsdirectory.com/skills/binbin-miao-mcp-builder)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: mcp-builder
description: "Designs and builds high-quality, agent-ergonomic Model Context Protocol (MCP) servers and tools following Anthropic official patterns."
---

# /mcp-builder — 高质量 MCP Server 与 Agent 工具构建规范

源自 `anthropics/skills`(`skills/mcp-builder`):

## 核心设计准则
1. **面向完整工作流封装(Deep Module Tools)**:围绕高层用户意图设计高信噪比工具,而非将底层碎片 CRUD 接口 1:1 暴露。
2. **严密自解释的输入 Schema**:使用 Pydantic / Zod 明确参数类型、默认值、约束与示例。
3. **输出控量与分页截断**:内置结果分页、字段过滤与长度截断,防止大体积原始数据撑爆模型上下文。
4. **可操作的错误反馈与安全注解**:报错时明确返回修正建议;准确标注 `readOnlyHint`、`destructiveHint` 与 `idempotentHint`。

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.