广告合作
MCP.so
登录

MCP Advisor已精选

@istarwyh

代码仓库

基本信息

分类

其他

许可证

MIT

传输方式

stdio

作者

istarwyh

提交者

Yihui Wang

关于 MCP Advisor

MCP Advisor & Installation - Use the right MCP server for your needs

#mcp-advisor#model-context-protocol#ai-assistant

MCP Advisor 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcpadvisor": {
      "command": "npx",
      "args": [
        "-y",
        "@xiaohui-wang/mcpadvisor"
      ]
    }
  }
}

MCP Advisor 工具

2

此工具用于寻找合适且专业MCP服务器。 基于您的具体需求，从互联网资源库以及内部MCP库中筛选并推荐最适合的MCP服务器解决方案。 返回结果包含服务器名称、功能描述、所属类别，为您的业务成功提供精准技术支持。

此工具用于安装MCP服务器。 请告诉我您想要安装哪个 MCP 以及其 githubUrl,我将会告诉您如何安装对应的 MCP

概览

What is MCP Advisor?

MCP Advisor is a discovery and recommendation service that helps AI assistants explore Model Context Protocol (MCP) servers using natural language queries. It is designed for developers and users who need to find and leverage MCP tools for specific tasks.

How to use MCP Advisor?

Integrate MCP Advisor by adding its configuration to your AI assistant’s MCP settings file (e.g. claude_desktop_config.json) with npx -y @xiaohui-wang/mcpadvisor. Once configured, you can query it with prompts such as "Find MCP servers for insurance risk analysis". Alternatively, install via Smithery with npx -y @smithery/cli install @istarwyh/mcpadvisor --client claude.

Key features of MCP Advisor

  • Natural‑language discovery of MCP servers
  • Multiple search providers (Meilisearch, GetMCP, Compass, Nacos, Offline)
  • Hybrid search combining text matching and vector search
  • Supports Stdio, SSE, and REST transports
  • Optional local Meilisearch for improved recommendation quality
  • Installation of MCP servers via direct prompts

Use cases of MCP Advisor

  • Quickly find MCP servers for a domain (e.g., natural language processing)
  • Install and configure MCP servers from a GitHub URL using a chat prompt
  • Integrate MCP server discovery into AI assistants or agent workflows
  • Offline or local search for MCP servers using a local Meilisearch instance

常见问题

1

What runtime does MCP Advisor require?

MCP Advisor runs via `npx`, so Node.js must be installed on the system. No additional runtime is required beyond the Node.js ecosystem.

2

Which search providers does MCP Advisor support?

It supports Meilisearch, GetMCP, Compass, Nacos, and an offline hybrid search provider that combines text matching and vector search.

3

Can I run MCP Advisor completely offline?

Yes, by starting a local Meilisearch instance with `pnpm meilisearch:start` and enabling it with the `--local-meilisearch` flag, you can use offline search without external APIs.

4

What transport methods are available?

Three transport methods are supported: Stdio (default for CLI), SSE (for web integration), and REST API endpoints.

5

Where does MCP Advisor store its data?

Search results are fetched from remote MCP registries (GetMCP, Compass) or from a local Meilisearch instance you configure. No data is stored persistently on your machine unless you run the local Meilisearch.

评论

其他 分类下的更多 MCP 服务器

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

广告合作