MCP-SSE Server

by sidharthrajaram

Backend/Servers SSE Server-Sent Events Cloud-Native API

This project demonstrates a working pattern for SSE-based MCP servers and standalone MCP clients. It allows for decoupled processes in cloud-native use-cases, unlike the STDIO-based pattern.

View on GitHub

Last updated: N/A

What is MCP-SSE Server?

This is an SSE-based MCP (Model Context Protocol) server and client implementation. It provides a way for agents (clients) to connect to, use, and disconnect from MCP servers over SSE, enabling decoupled processes.

How to use MCP-SSE Server?

Ensure you have an Anthropic API key in .env or as an environment variable.
Run the server using uv run weather.py (optionally specify host and port with --host and --port).
Run the client using uv run client.py http://0.0.0.0:8080/sse (adjust the URL to match your server's address).

Key features of MCP-SSE Server

SSE-based communication
Decoupled server and client processes
Cloud-native architecture
Integration with National Weather Service APIs (in example)
Smithery installation support

Use cases of MCP-SSE Server

Connecting agents to remote MCP servers
Building cloud-native applications with MCP
Creating decoupled microservices
Integrating with external APIs via MCP
Developing AI assistants and tools

FAQ from MCP-SSE Server

What is MCP?

MCP stands for Model Context Protocol. It's a protocol for interacting with language models and tools.

What is SSE?

SSE stands for Server-Sent Events. It's a server push technology enabling real-time data streaming from a server to a client.

Why use SSE for MCP?

SSE allows for a more decoupled and cloud-native architecture compared to STDIO-based implementations.

How do I configure the server?

You can configure the server's host and port using command-line arguments like uv run weather.py --host <your host> --port <your port>.

How do I install this via Smithery?

Use the command npx -y @smithery/cli install @sidharthrajaram/mcp-sse --client claude