MCP SSE Client-Server

@flyingcloud-code

About MCP SSE Client-Server

using sse in client and server

Basic information

Category

Other

License

MIT

Runtime

python

Transports

stdio

Publisher

flyingcloud-code

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-sse-client-server": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP SSE Client-Server?

A Python implementation of an MCP client and server that communicates using Server-Sent Events (SSE). It integrates with MCP platform tools for web search, content retrieval, and date/weather utilities, and is intended for developers building asynchronous AI assistants.

How to use MCP SSE Client-Server?

Clone the repository, create a virtual environment, and install dependencies with uv sync .. Configure API keys in a .env file (OpenAI or OpenRouter). Start the server first with uv run mcp-server-search.py, then run the client with uv run mcp-client-sse.py --server http://localhost:8081/sse --verbose. Use --help for full options.

Key features of MCP SSE Client-Server

SSE-based communication between client and server
Integration with MCP platform tools (google_search, get_web_content)
Asynchronous processing using Python's asyncio
Comprehensive logging and error handling
OpenAI API integration with fallback to OpenRouter
Environment variable configuration support

Use cases of MCP SSE Client-Server

Perform web searches via the google_search MCP tool
Fetch full content of web pages with get_web_content
Retrieve the weekday for a given date
Get weather information for a specific date
Build real-time streaming AI assistants with MCP

FAQ from MCP SSE Client-Server

What runtime is required?

Python 3.10 or higher. Dependencies include httpx, python-dotenv, openai, and mcp[cli].

How do I configure API keys?

Create a .env file in the project root with either OPENAI_API_KEY or OPENROUTER_API_KEY. Optionally set custom base URLs.

What transport does the server use?

The server uses Server-Sent Events (SSE) over HTTP. The default server URL is http://localhost:8081/sse.

Where are logs stored?

The client writes logs to mcp-client.log with timestamps and detailed information.

Can I use OpenRouter instead of OpenAI?

Yes. If you set OPENROUTER_API_KEY in your .env file, the client will fall back to OpenRouter. You can also specify a custom base URL.

Comments

More Other MCP servers

Maestro

Painless E2E Automation for Mobile and Web

Codelf

A search tool helps dev to solve the naming things problem.

FastMCP v2 🚀

🚀 The fast, Pythonic way to build MCP servers and clients.

Awesome Mcp Servers

A collection of MCP servers.

Blender

Open-source MCP to use Blender with any LLM