Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

mcp-expertMCP expert 搜索

Agent Skill

mcp-expert 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

336

周安装

14

GitHub Stars

9

下载量

112
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:mcp-expert(MCP expert 搜索)
来源仓库:https://github.com/yuniorglez/gemini-elite-core
仓库路径:skills/mcp-expert
安装命令:
npx skills add https://github.com/yuniorglez/gemini-elite-core --skill mcp-expert
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yuniorglez/gemini-elite-core --skill mcp-expert

简介

用于查找、检索和筛选相关信息,支持快速定位候选结果。

  • 适合根据关键词、任务场景或来源线索进行信息收集。
  • 安装命令:npx skills add https://github.com/yuniorglez/gemini-elite-core --skill mcp-expert。
  • 使用前建议确认权限范围和是否会触发联网或文件操作。
  • 可参考来源仓库 README 了解具体搜索逻辑和输出格式。

SKILL.md

🛠️ Skill: mcp-expert (v1.4.0)

Executive Summary

mcp-expert is the definitive resource for building and managing Model Context Protocol (MCP) ecosystems. In 2026, MCP is the backbone of autonomous AI agents, enabling them to navigate complex data, interact with legacy APIs, and render dynamic user interfaces. This skill covers the entire lifecycle—from proactive onboarding to advanced MCP App development and high-security server orchestration.


📋 Table of Contents

  1. Core Capabilities
  2. The "Do Not" List (Anti-Patterns)
  3. Quick Start: Onboarding Protocol
  4. Standard Production Patterns
  5. Professional Server Engineering
  6. Security & Zero-Trust Auth
  7. MCP Apps: Interactive Outcomes
  8. Reference Library

🚀 Core Capabilities

  • Proactive Onboarding: Automatically detecting and configuring missing MCP servers.
  • Agentic Tool Design: Crafting outcome-oriented tool interfaces for LLM excellence.
  • Multimodal Interaction: Leveraging resources for long-form data (Video, PDF) via MCP URIs.
  • Interactive UI Rendering: Implementing MCP Apps for direct user-agent interaction.
  • Resilient Orchestration: Managing tool timeouts, pagination, and error recovery.

🚫 The "Do Not" List (Anti-Patterns)

Anti-PatternWhy it fails in 2026Modern Alternative
Chatty APIsWastes LLM tokens and increases latency.Use Outcome-Oriented Tools.
Raw ExceptionsLLM cannot self-correct from stack traces.Return Helpful Error Strings.
Hardcoded SecretsMassive security vulnerability.Use Environment Variable Mapping.
Stdout LoggingBreaks the Stdio transport channel.Log only to Stderr.
Monolithic ServersHard to maintain and discover.Use Focused, Small Servers (5-15 tools).

⚡ Quick Start: Onboarding Protocol

When an agent needs a new capability (e.g., "Search the web"):

  1. Validation: Check if the required MCP server is already active.
  2. Guide: If missing, provide the user with a direct installation path.

- *"I need to browse the web. I'll setup the browser-use MCP server now."*

  1. Config: Use uvx for zero-install execution where possible.
"browser-use": {
  "command": "uvx",
  "args": ["mcp-server-browser-use", "server"],
  "env": { "BROWSER_USE_API_KEY": "..." }
}

🛠 Standard Production Patterns

Pattern A: The "Progressive Disclosure" Resource

For large datasets, don't return all data. Return a list of URIs.

  • mcp://sales/2026/summary
  • mcp://sales/2026/detailed-report

Pattern B: The "Retryable" Tool

Tools that return a retry_with suggestion if inputs are slightly off.


⚙️ Professional Server Engineering

Building a high-performance server in 2026:

  • Runtime: Bun.
  • Validation: Zod.
  • Standard: 2025-11-25 Specification.

*See References: Server Development for the blueprint.*


🔒 Security & Zero-Trust Auth

  • OAuth 2.1: Mandatory for enterprise data access.
  • Capability Scopes: Limit the agent to the task at hand.
  • HITL Gate: Human-in-the-loop approval for destructive actions.

*See References: Security & Auth for implementation.*


🖥️ MCP Apps: Interactive Outcomes

MCP Apps are the next evolution of AI interfaces.

  • Live Dashboards.
  • Interactive File Editors.
  • Visual Selection Tools.

*See References: MCP Apps for architectural details.*


📖 Reference Library

Detailed deep-dives into MCP excellence:


*Updated: January 22, 2026 - 17:35*

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.39%
按下载量换算39

Claude

31.87%
按下载量换算36

Cursor

19.39%
按下载量换算22

Gemini CLI

8.26%
按下载量换算9

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills