広告掲載
MCP.so
ログイン

MCP Server and Google ADK Multi-Tool System

@ammilam

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT license

トランスポート

stdio

作者

ammilam

MCP Server and Google ADK Multi-Tool System について

概要はまだありません

MCP Server and Google ADK Multi-Tool System 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": {
    "mcp-server-google-adk-sse-multi-tool-system": {
      "command": "python",
      "args": [
        "-m",
        "mcp_agent.main"
      ]
    }
  }
}

MCP Server and Google ADK Multi-Tool System 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 MCP Server and Google ADK Multi-Tool System?

It is a system combining an MCP Server (TypeScript/Express) that provides tools for file operations, API calls, session data management, and weather information, with a Google ADK Agent (Python) that uses these tools through a webhook interface. It is intended for developers who want to build AI agents with custom tool capabilities.

How to use MCP Server and Google ADK Multi-Tool System?

Run ./scripts/setup.sh to set up both components. Configure .env files for the MCP server and the Google ADK agent with required tokens and project IDs. Start the MCP server with ./scripts/run-mcp.sh and the ADK agent with adk web. Open http://localhost:8000, select mcp_agent, and chat with the agent to test.

Key features of MCP Server and Google ADK Multi-Tool System

  • Default tools: file system, API calls, session data management, and weather.
  • Communicates with Google ADK agents via a webhook endpoint.
  • Supports adding new custom tools with a documented step-by-step process.
  • Provides dedicated REST endpoints per session for each tool.
  • Emits SSE events for real-time updates to clients.
  • Manages session state across multiple tool calls.

Use cases of MCP Server and Google ADK Multi-Tool System

  • Creating an AI agent that can read, write, and manage files on a server.
  • Building a conversational assistant that calls external APIs and returns results.
  • Integrating weather data into a chat agent for real-time queries.
  • Extending an agent with image generation capabilities (e.g., from text prompts).
  • Managing session-specific data across multiple turns of a conversation.

よくある質問

1

What are the prerequisites?

You need Node.js (v16+), Python (v3.9+), the Google ADK SDK (`pip install google-adk`), a Google Cloud project with Vertex AI enabled, IAM permissions for the agent, and GitHub/GitLab access tokens if using repository tools.

2

How does the Google ADK agent communicate with the MCP server?

The agent sends HTTP POST requests to the MCP server’s `/api/adk-webhook` endpoint. The MCP server processes the request and returns

コメント

「その他」の他のコンテンツ

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

ICSS

chokcoco

不止于 CSS

20.7K

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

広告掲載