MCP.so
ログイン

Unified MCP Suite

@Godzilla675

基本情報

カテゴリ

推論

トランスポート

stdio

作者

Godzilla675

Unified MCP Suite について

A suite of Model Context Protocol (MCP) servers designed to enhance AI agent capabilities. Provides tools for media search/understanding (images, video), web information retrieval, PDF generation, and PowerPoint presentation creation, enabling agents to interact with diverse data

#agentic-ai#ai-tool-suite#media-retrieval

Unified MCP Suite 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": {
    "agentic-ai-tool-suite": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

Unified MCP Suite 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。

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 Unified MCP Suite?

Unified MCP Suite is a collection of Model Context Protocol (MCP) servers packaged together for convenience, providing media handling, information retrieval, and document creation capabilities for AI assistants.

How to use Unified MCP Suite?

The easiest way is to use npx to run the published npm packages (e.g., npx -y information-retrieval-mcp-server) and configure each server individually in your MCP client's settings file. Alternatively, clone the repository and build each server from source.

Key features of Unified MCP Suite

  • Search images via Unsplash and videos via YouTube.
  • Download and understand image/video content using Google Gemini.
  • Perform web searches with Google Custom Search and crawl web pages.
  • Generate PDF documents from HTML content using Playwright.
  • Create PowerPoint presentations from HTML slides.

Use cases of Unified MCP Suite

  • Search for images and videos and have their content understood by an LLM.
  • Retrieve up-to-date information from web searches and page crawling.
  • Produce PDF reports or documents from raw HTML.
  • Assemble slide presentations and PDFs from HTML content.

よくある質問

1

What are the runtime requirements for Unified MCP Suite?

The TypeScript/Node.js servers require Node.js and npm. The Python servers require Python 3, a virtual environment, and Playwright browsers (`playwright install`).

2

Where do API keys go?

API keys are set as environment variables in the MCP client configuration file (e.g., `GOOGLE_API_KEY`, `UNSPLASH_ACCESS_KEY`). See the example `claude_desktop_config.json`.

3

Which servers require no API keys?

The PDF Creator Server and Presentation Creator Server require no API keys. All other servers need at least one external API key.

4

How are the servers started?

Once configured in the MCP client's settings file, the servers start automatically when the client launches and communicate via stdio.

5

Can I use Unified MCP Suite with any MCP client?

Yes, it is designed for MCP clients like Cline or the Claude Desktop App, configured via `cline_mcp_settings.json` or `claude_desktop_config.json`.

コメント

「推論」の他のコンテンツ