广告合作
MCP.so
登录

Multiple MCP SSE Servers with a Python Host

@hackerinheels

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

hackerinheels

关于 Multiple MCP SSE Servers with a Python Host

This repository contains a python implementation of an MCP Host which is capable of running several MCP Servers with SSE protocol

#multiplemcp#sse#python#server

Multiple MCP SSE Servers with a Python Host 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "multipleMCPServerWithPythonHost": {
      "command": "uv",
      "args": [
        "venv",
        "--python",
        "3.11"
      ]
    }
  }
}

Multiple MCP SSE Servers with a Python Host 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Multiple MCP SSE Servers with a Python Host?

Multiple MCP SSE Servers with a Python Host is a Server-Sent Events (SSE) Model Context Protocol (MCP) client implementation that uses Google’s Gemini API. It reads a config.json file to launch and maintain connections with multiple MCP servers, and handles lifecycle management and cleanup. It is intended for developers who want to run several MCP servers concurrently and interact with them through a single Python host.

How to use Multiple MCP SSE Servers with a Python Host?

Clone the repository, create a .env file with GEMINI_API_KEY and MODEL_NAME, set up Google Calendar API credentials, update config.json with the MCP server commands, then run uv run host.py from a Python 3.11+ virtual environment. Interact by typing queries in the client prompt.

Key features of Multiple MCP SSE Servers with a Python Host

  • Launches and manages multiple MCP servers from a single config file.
  • Uses SSE transport for server communication.
  • Integrates with Google’s Gemini API for LLM responses.
  • Supports calendar management and browser automation servers.
  • Handles graceful shutdown and cleanup automatically.
  • Can be packaged as a distributable DMG on macOS.

Use cases of Multiple MCP SSE Servers with a Python Host

  • Automate calendar event queries alongside web browsing tasks.
  • Build a multi-tool assistant that can read calendars and control a browser.
  • Prototype an MCP host that connects several third-party MCP servers.
  • Distribute a pre-configured host application for end users.

常见问题

1

What transport protocol does the host use?

The host uses Server-Sent Events (SSE) for communication with MCP servers. STDIO server support is planned but not yet implemented.

2

Which LLM model is required?

The example configuration uses Google Gemini 2.0 Flash (`gemini-2.0-flash`). The API key must be set in the `.env` file under `GEMINI_API_KEY`.

3

What dependencies are needed to run the host?

Python 3.11+, the UV package manager, a Gemini API key, and Google Calendar API credentials (if using the calendar server). For the browser server, Google Chrome must be installed and the `CHROME_PATH` environment variable set.

4

Can I use a different LLM model?

Currently only Gemini models are supported. The README lists multiple model support as a planned future feature.

5

Where does data live and what are known limitations?

User queries and server responses are handled in memory; no persistent storage is described. Limitations include no STDIO server support, no multiple model support, and no tool chaining yet (all noted as “Todo”). Authentication relies on API keys in environment variables.

评论

其他 分类下的更多 MCP 服务器

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Soar Flight Booking MCP

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K
广告合作