MCP.so
ログイン

Need

@tuckerschreiber

リポジトリ

Need について

AI agents hallucinate package names. need gives them a verified index of 10,000+ CLI tools — semantic search across brew, npm, pip, apt, and cargo with a feedback loop that gets smarter with every install.

#cli#mcp#tool-discovery#ai-agents#semantic-search

基本情報

カテゴリ

その他

トランスポート

stdio

公開者

tuckerschreiber

投稿者

tuckerschreiber

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "need": {
      "command": "npx",
      "args": [
        "@agentneeds/need",
        "serve"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Need?

Need is a CLI tool discovery service for AI agents that provides a verified index of 10,000+ CLI tools and a feedback loop that improves with every install, preventing agents from hallucinating package names.

How to use Need?

Install globally via npm install -g @agentneeds/need, which auto-configures for Claude Code, Cursor, and Claude Desktop. Alternatively, try without installing by running npx @agentneeds/need "compress png images". Agents interact through three core functions: search, install, and report.

Key features of Need

  • Verified index of 10,000+ CLI tools
  • Search with ranked results for agent queries
  • Install tools via brew, apt, npm, pip, or cargo
  • Report tool usage to improve future rankings
  • Feedback loop that gets smarter with each install
  • Auto-configures for Claude Code, Cursor, and Claude Desktop

Use cases of Need

  • An agent searches for a tool to compress PNG images and gets ranked suggestions
  • An agent installs a tool identified by name across multiple package managers
  • An agent reports successful or failed tool usage to refine the index
  • Developers integrate Need into their AI workflow to avoid hallucinated package names

FAQ from Need

—

コメント

「その他」の他のコンテンツ

Production-ready MCP integrations for AI applications

Klavis-AI

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

5.8K

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

Nginx UI

0xJacky

Yet another WebUI for Nginx

11.3K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Unity MCP ✨

justinpbarnett

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

12.2K