mcp-server-google-adk-sse-multi-tool-system

ammilam/mcp-server-google-adk-sse-multi-tool-system

3.3

If you are the rightful owner of mcp-server-google-adk-sse-multi-tool-system and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Model Context Protocol (MCP) server is a TypeScript/Express server designed to provide a suite of tools for file operations, API calls, session data management, and weather information. It works in conjunction with a Google ADK agent to process user requests and perform various operations.

The MCP server is a robust backend system that facilitates seamless interaction between users and a variety of tools through a Google ADK agent. It is built using TypeScript and Express, ensuring a scalable and efficient server environment. The server is designed to handle multiple types of operations, including file management, API interactions, session data handling, and weather information retrieval. By leveraging a webhook interface, the MCP server processes requests from the Google ADK agent, executes the necessary operations, and returns the results. This setup allows for a modular and extensible architecture, making it easy to add new tools and capabilities. The server also supports real-time updates through Server-Sent Events (SSE), providing users with immediate feedback on their requests. With its comprehensive toolset and flexible design, the MCP server is an ideal solution for integrating various functionalities into a cohesive system.

Features

  • TypeScript/Express server for efficient and scalable operations
  • Integration with Google ADK agent for seamless user interaction
  • Support for file operations, API calls, session data management, and weather information
  • Modular architecture for easy addition of new tools
  • Real-time updates through Server-Sent Events (SSE)

Usages

usage with local integration stdio

python
mcp.run(transport='stdio')  # Tools defined via @mcp.tool() decorator

usage with local integration subprocess

python
command='uv', args=['run', 'server.py']  # Launch using virtual environment

usage with remote integration sse

python
mcp.run(transport='sse', host="0.0.0.0", port=8000)  # Specify SSE endpoint

usage with remote integration streamable http

yaml
paths:
  /mcp:
    post:
      x-ms-agentic-protocol: mcp-streamable-1.0  # Copilot Studio integration

usage with platform integration github

{"command": "docker", "args": ["run", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"]}

usage with platform integration copilot studio

yaml
paths:
  /mcp:
    post:
      x-ms-agentic-protocol: mcp-streamable-1.0  # Copilot Studio integration

usage with development framework fastmcp

python
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...

Tools

  1. file_system

    Handles file operations such as reading, writing, listing, and deleting files.

  2. api_call

    Facilitates making API calls to external services.

  3. session_data

    Manages session data storage and retrieval.

  4. weather

    Provides weather information for specified locations.