MCP Compass
MCPコンパス🧭
MCPの発見と推奨
MCP コンパスを体験する 🌐
MCP の検出を当社の Web サイトで直接体験できるようになりました。
👉 **MCPコンパスを探索する**👈
リアルタイムの推奨事項と洞察を活用した MCP サービスの実際の威力を詳しくご覧ください。
Related MCP server: MCPfinder Server
これは何ですか?🤔
MCP Compassは、モデルコンテキストプロトコル(MCP)サーバーの探索を支援する発見・推奨サービスです。AIアシスタントが自然言語クエリに基づいて利用可能なMCPサービスを発見・理解するのに役立つスマートガイドとして機能し、特定のタスクに適したツールの発見と活用を容易にします。
簡単な例
特徴 🌟
🔍スマート検索: 自然言語クエリを使用して MCP サービスを検索します
📚豊富なメタデータ:各サービスに関する詳細な情報を取得
🔄リアルタイム更新:最新のMCPサービスを常に最新の状態に保ちます
🤝簡単な統合:MCP 対応の AI アシスタントと簡単に統合できます
クイックスタート 🚀
使用法
リポジトリをクローンする
または
npxを使用する
インストール
Claude Desktop の場合は、 claude_desktop_config.jsonファイルを編集します。
MacOS/Linux
code ~/Library/Application\ Support/Claude/claude_desktop_config.jsonウィンドウズ
code $env:AppData\Claude\claude_desktop_config.jsonMCPサービスとして:
AI アシスタントの MCP 構成に追加して、サービス検出機能を有効にします。
{ "mcpServers": { "mcp-compass": { "command": "npx", "args": [ "-y", "@liuyoshio/mcp-compass" ] } } }または
{ "mcpServers": { "mcp-compass": { "command": "node", "args": [ "/path/to/repo/build/index.js" ] } } }
ライセンス📝
MIT ライセンス - 詳細についてはLICENSEファイルを参照してください。
サポート💬
Available Tools
1 toolrecommend-mcp-serversB
Use this tool when there is a need to findn external MCP tools. It explores and recommends existing MCP servers from the internet, based on the description of the MCP Server needed. It returns a list of MCP servers with their IDs, descriptions, GitHub URLs, and similarity scores.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as recommending MCP servers based on descriptions, and no other tools exist to cause confusion.
A single tool inherently exhibits perfect naming consistency, as there are no other tools to compare against. The tool name 'recommend-mcp-servers' follows a clear verb-noun pattern and uses hyphens consistently.
One tool is too few for a server named 'MCP Compass', which suggests a broader scope of functionality for exploring or navigating MCP servers. A single recommendation tool feels thin and incomplete for this apparent purpose, lacking supporting tools like search, filter, or get details.
The tool surface is severely incomplete for the inferred domain of MCP server exploration. While the tool can recommend servers, there are significant gaps: no ability to search, filter, get detailed information, list categories, or manage preferences. This will likely cause agent failures when trying to perform comprehensive MCP server discovery tasks.
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA discovery and recommendation service that helps AI assistants find Model Context Protocol servers based on natural language queries.57 npm90MIT
- AlicenseAqualityNot gradedmaintenanceEnables AI assistants to discover, retrieve details about, and manage MCP (Model Context Protocol) servers that provide additional tools and capabilities on demand.563 npm10-
- FlicenseNot gradedqualityDmaintenanceAn intelligent server that helps discover and research MCP servers using the Exa AI search engine, enabling users to find appropriate Model Context Protocol servers for specific requirements.3-
- AlicenseNot gradedqualityDmaintenanceA powerful orchestration layer for Model Context Protocol (MCP) servers that enables AI assistants to dynamically discover, inspect, and interact with multiple MCP servers through a unified interface.MIT