
istarwyh/mcpadvisor 是一个从 https://github.com/istarwyh/mcpadvisor. 导入的 MCP 服务器候选
概览
istarwyh/mcpadvisor 是一个从 https://github.com/istarwyh/mcpadvisor. 导入的 MCP 服务器候选
概述(AI 翻译)
英文 |简体中文
引言
MCP Advisor 是一款发现和推荐服务,帮助 AI 助手利用自然语言查询探索模型上下文协议(MCP)服务器。它使用户更容易找到并利用适合特定任务的 MCP 工具。
用户故事
- 发现并推荐MCP服务器
- 作为一名AI代理开发者,我想通过自然语言查询快速找到适合特定任务的MCP服务器。
- 示例提示:
"Find MCP servers for insurance risk analysis"
- 安装并配置MCP服务器
- 作为一名发现有用MCP服务器的普通用户,我想尽快安装并开始使用它。
- 示例提示:[
"Install this MCP: https://github.com/Deepractice/PromptX"
演示
https://github.com/user-attachments/assets/7a536315-e316-4978-8e5a-e8f417169eb1
用途
配置完成后,Nacos 提供者将自动启用,并在搜索 MCP 服务器时使用。您可以使用自然语言查询,例如:
更具体地说:
文档导航
- 快速入门指南 - 安装、配置及基本使用方法
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
MCP Advisor
MCP Advisor helps an MCP client discover servers for a task and obtain installation guidance. It aggregates search providers and returns recommendations; it does not install a server, edit your client configuration, or verify a recommended server’s safety for you.
Start here
- Use the current source: follow the Quick Start for MCP 2026-07-28 clients, stdio, or HTTP.
- Need an older client? The published npm version
1.0.5is a separate legacy release. Do not apply the current source’s transport configuration to it. - Develop or diagnose: read Contributing, Architecture, and Technical Reference. For current protocol failures, start with the migration guide.
Award and project background
MCP Advisor is developed by the mcpadvisor team, which won second prize at the
inaugural OceanBase AI Hackathon in 2025 (首届 OceanBase AI 黑客松大赛).
The organizer’s May 19 event report
names the team and describes its MCP search and recommendation project; the event
concluded in Guangzhou on May 17, 2025.
The author’s OceanBase community post
connects that project to this repository. This is historical recognition, not a
benchmark or endorsement of every current feature.
What is available?
| Capability | Current-source status |
|---|---|
recommend-mcp-servers |
Task-based recommendations with optional keywords/capabilities |
install-mcp-server |
Installation guidance/configuration text only; no automatic installation |
| Meilisearch, Compass, GetMCP | Constructed by the CLI; external availability/configuration still matters |
| Offline provider | Enabled by SearchService by default; embeddings can require a model download |
| Nacos discovery | Opt-in; CLI requires address, username and password |
| Cline Marketplace | Implemented, opt-in via CLINE_MARKETPLACE_ENABLED=true |
| FlashRank reranking | Implemented, default off; separately started Python service and model |
| Search-quality evaluation | Evaluation tooling and illustrative fixtures; not proof of production quality |
| Automatic installation / quality guarantees | Not implemented / not established |
The active Meilisearch provider uses text search. Offline retrieval combines text and vectors; this is not universal vector search, adaptive query weighting, or a guarantee of five results. Online providers still run alongside offline data.
Choose a runtime
Current source (modern protocol)
Use Node.js 20+ for the application; Inspector 2.10.1 additionally requires Node.js
22.19+. Use the pinned pnpm 8.15.9 from package.json.
git clone https://github.com/istarwyh/mcpadvisor.git
cd mcpadvisor
corepack enable
pnpm install --frozen-lockfile
安装
npx -y @xiaohui-wang/[email protected]