広告掲載
MCP.so
ログイン

302 Basic MCP Server

@302ai

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

302ai

投稿者

Jomy Wu

302 Basic MCP Server について

提供搜索/代码运行/计算器/网页解析/网页部署等基本功能。

#mathgpt#math-solver#math-assistant

302 Basic MCP Server の設定

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": {
    "302ai-basic-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@302ai/basic-mcp"
      ],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

302 Basic MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is 302_basic_mcp?

302_basic_mcp is a Model Context Protocol server that provides a toolkit of fundamental utilities—such as web search, code execution, file parsing, and more—to enhance the capabilities of large language models. It is aimed at developers who want to equip MCP-compatible clients (e.g., Claude Desktop, Cherry Studio, ChatWise) with practical, ready-to-use tools.

How to use 302_basic_mcp?

Install and run via npx -y @302ai/basic-mcp, then configure your MCP client (Claude Desktop, Cherry Studio, or ChatWise) with the provided JSON block, setting your 302AI_API_KEY in the environment variables. The server supports both local stdin mode and a remote HTTP server mode.

Key features of 302_basic_mcp

  • Dynamic tool list loaded from a remote server
  • Supports stdin (local) and HTTP server (remote) modes
  • Includes tools: Wiki Search, Arxiv Search, Calculator, Code Execution, Web Search, File Parser
  • Simple npx-based installation with no additional dependencies required
  • Compatible with multiple MCP clients (Claude Desktop, Cherry Studio, ChatWise)

Use cases of 302_basic_mcp

  • Enable an LLM to perform live web searches during a conversation
  • Run calculations or execute code snippets directly through the model
  • Search and retrieve academic papers from Arxiv
  • Parse and extract content from uploaded files
  • Combine multiple basic tools to answer complex, multi-step queries

よくある質問

1

How do I get the 302AI_API_KEY?

Sign in at [https://dash.302.ai/apis/list](https://dash.302.ai/apis/list) to create or retrieve your API key. Tutorials are available at [https://help.302.ai/en/docs/API-guan-li](https://help.302.ai/en/docs/API-guan-li).

2

Which MCP clients are supported?

The README provides configuration examples for **Claude Desktop**, **Cherry Studio**, and **ChatWise**. Other clients that support the standard MCP protocol should also work.

3

What runtime or dependencies are required?

You only need **Node.js** and `npx` (bundled with npm). The server runs via `npx -y @302ai/basic-mcp`, which automatically downloads the package.

4

How can I debug the server?

Run `npm run inspector` in the project directory. This starts the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) and provides a URL for browser-based debugging tools.

5

Can the server run as a remote HTTP service?

Yes. The README mentions "Multi modes supported, you can use `stdin` mode locally, or host it as a remote HTTP server." No configuration details for the HTTP mode are provided beyond that statement.

コメント

「その他」の他のコンテンツ

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

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

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
広告掲載