Server profile

MCP Advisor

MCP Advisor helps assistants discover MCP servers from natural-language requests and obtain installation guidance. It combines registry providers with offline search and offers optional local Meilisearch integration.

Server facts

MCP Advisor

Project

Author
istarwyh
License
MIT

Tech

Runtime / language
nodeTypeScript
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
89
Last commit
Data as of

Tags

  • Hybrid Search
  • Mcp Discovery
  • Meilisearch
  • Server Recommendations

Overview

MCP Advisor is a discovery service for assistants and developers who need to identify MCP servers for a particular task. Instead of requiring a known repository name, it accepts natural-language descriptions and returns candidate servers with descriptive information. Its installation tool provides guidance when given a server and its GitHub URL. The README illustrates both task-oriented discovery and a follow-up installation request, making the project relevant to users choosing integrations as well as developers building agents. The recommendation layer can combine multiple providers, merge their results, and apply configurable limits or similarity thresholds rather than depending on one registry alone.

The documented architecture includes Meilisearch, GetMCP, Compass, Nacos, and an offline provider. Offline retrieval mixes textual matching with vector search, while Nacos supports service discovery. A local Meilisearch instance is optional and is presented as a way to improve recommendations; the README provides a bootstrap command and a launch flag for that mode. The standard client configuration starts the npm package through npx using stdio. SSE and REST interfaces are also described for web integrations, and a SearchService export supports library use. Registry connectivity matters when troubleshooting empty results. The README separates future orchestration and learning ambitions into a roadmap, so those plans should not be treated as delivered discovery features.

Install & configure

Requirements

  • npx
  • An MCP-compatible client
Documented launch / install command
npx -y @xiaohui-wang/mcpadvisor

Stdio is the default. Local Meilisearch is optional; the README also describes SSE and REST interfaces.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

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

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

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

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "mcpadvisor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@xiaohui-wang/mcpadvisor"
      ],
      "env": {}
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

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

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "mcpadvisor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@xiaohui-wang/mcpadvisor"
      ],
      "env": {}
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
recommend-mcp-serversFind candidate MCP servers for a task using registry and internal search sources.
install-mcp-serverProvide installation guidance for a specified MCP server and GitHub URL.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Find task-specific MCP integrations from plain-language requests
  • Get installation guidance for a discovered GitHub project
  • Add server discovery to a custom agent through SearchService
  • Use optional local Meilisearch for recommendations

Strengths

  • Aggregates multiple search providers
  • Offers offline hybrid text and vector retrieval
  • Includes both discovery and installation-guidance tools

Limitations

  • Registry API connectivity can affect search results
  • Local Meilisearch adds a separate service to configure

Frequently asked questions

Yes. The README shows task descriptions being used to search for suitable MCP servers.

No. A local instance is described as an optional improvement to recommendations.

Stdio is the default CLI transport; SSE and REST options are also documented.

The supplied tool description asks for the desired MCP server and its GitHub URL to provide installation instructions.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Serena

Developer Tools

Serena gives coding agents symbol-aware retrieval, editing, refactoring, and debugging capabilities through MCP. It uses language servers or a JetBrains plugin to bring IDE-style code understanding to existing AI clients.

Context7

Developer Tools

Context7 retrieves current library documentation and code examples for AI coding assistants. It supports MCP tools or a CLI-and-skills workflow, with library IDs and version-aware requests helping narrow the documentation context.

FastAPI-MCP

Developer Tools

FastAPI-MCP exposes existing FastAPI endpoints as MCP tools while retaining schemas, endpoint documentation, and dependency-based authentication. It is a native extension for developers adding agent access to a FastAPI service.

GitMCP

Developer Tools

GitMCP turns public GitHub repositories and GitHub Pages projects into documentation sources for AI assistants. It offers repository-specific endpoints or a dynamic server for retrieving docs, searching code, and following referenced content.

XcodeBuildMCP

Developer Tools

XcodeBuildMCP provides an MCP server and CLI for AI agents working on iOS and macOS projects. One package supports direct terminal tools, simulator builds, and stateful operations such as debugging and log capture.

DevDocs by CyberAGI

Developer Tools

Crawl technical documentation into organized Markdown, JSON, and MCP-accessible content for development assistants. The public DevDocs repository is marked as not publicly maintained.

JetBrains MCP Proxy Server

Developer Tools

This legacy Node-based proxy connects MCP clients to a JetBrains IDE plugin. The repository is deprecated: IntelliJ-based IDEs include the core functionality from version 2025.2 onward.

MCP Language Server

Developer Tools

Expose an installed language server to MCP assistants for semantic code navigation and edits. It provides definitions, references, diagnostics, hover information, symbol renaming, and line-based file changes.