MCP SSE

v1.0.0Developer Toolsstable

A working pattern for SSE-based MCP clients and servers

agentsllmmcptool-use
Share:
301
Stars
0
Downloads
0
Weekly
0/5

What is MCP SSE?

MCP SSE is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to working pattern for sse-based mcp clients and servers

A working pattern for SSE-based MCP clients and servers

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A working pattern for SSE-based MCP clients and servers

Use Cases

Server-Sent Events MCP pattern
Streaming MCP implementation
Real-time agent communication
sidharthrajaram

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 17, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-sse

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP SSE

The MCP SSE project provides a reference implementation and working pattern for building Server-Sent Events (SSE) based MCP servers and standalone clients, demonstrating how to decouple MCP servers from clients so they can run as independent network-accessible processes. The repository includes a functional weather server built on the National Weather Service API and a generic SSE client that connects to any SSE-based MCP server endpoint. Developers building cloud-native or multi-process MCP architectures use it as a template for moving beyond the traditional stdio transport.

Prerequisites

  • Python 3.10 or higher with uv installed (pip install uv)
  • The mcp and httpx Python packages
  • An Anthropic API key (ANTHROPIC_API_KEY) for the bundled SSE client
  • An MCP client that supports SSE transport, or use the included client.py
1

Clone the repository

Clone the mcp-sse repository to get the weather server and client implementations.

git clone https://github.com/sidharthrajaram/mcp-sse.git
cd mcp-sse
2

Install dependencies

Install Python dependencies using uv or pip.

uv sync
# or: pip install -r requirements.txt
3

Set your Anthropic API key

The included client uses Claude to process tool results. Export your API key before running the client.

export ANTHROPIC_API_KEY=sk-ant-...
4

Start the SSE weather server

Launch weather.py to start the MCP server on port 8080. It exposes get_alerts and get_forecast tools over SSE.

uv run weather.py
5

Connect the SSE client

In a separate terminal, run client.py pointing at the server's SSE endpoint. You can now send natural language queries to the weather tools.

uv run client.py http://0.0.0.0:8080/sse
6

Install via Smithery for Claude Desktop

Use Smithery to register the server with Claude Desktop automatically if you want to use it within Claude rather than the standalone client.

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

MCP SSE Examples

Client configuration

Claude Desktop config for the SSE weather server running locally. Note that SSE transport support in Claude Desktop may require a compatible version.

{
  "mcpServers": {
    "mcp-sse-weather": {
      "command": "python",
      "args": ["weather.py"],
      "env": {
        "ANTHROPIC_API_KEY": "sk-ant-..."
      }
    }
  }
}

Prompts to try

Send weather queries through the SSE client to exercise the get_alerts and get_forecast tools.

- "What's the weather forecast for Chicago this weekend?"
- "Are there any severe weather alerts active in Florida right now?"
- "Get the current weather alerts for the state of California."
- "What will the weather be like in Denver, Colorado tomorrow?"
- "Check if there are any winter storm warnings in the Northeast US."

Troubleshooting MCP SSE

client.py cannot connect to the SSE endpoint

Ensure weather.py is running in a separate terminal first. Verify with `curl http://0.0.0.0:8080/sse` — you should see a persistent SSE stream. If the port is in use, restart with `uv run weather.py --port 8081` and update the client URL accordingly.

No forecast data returned for a location

The National Weather Service API only covers US locations. Non-US locations will return empty results. Provide US city names, state abbreviations, or coordinates.

uv command not found

Install uv with `pip install uv` or via the official installer: `curl -LsSf https://astral.sh/uv/install.sh | sh`. Alternatively, use `python weather.py` directly after installing requirements with pip.

Frequently Asked Questions about MCP SSE

What is MCP SSE?

MCP SSE is a Model Context Protocol (MCP) server that working pattern for sse-based mcp clients and servers It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP SSE?

Follow the installation instructions on the MCP SSE GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP SSE?

MCP SSE works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP SSE free to use?

Yes, MCP SSE is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-sse": { "command": "npx", "args": ["-y", "mcp-sse"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP SSE?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides