mcpField
M
MCP Client-Server

MCP Client-Server

Remote
github.com/duaraghav8Developer Tools3Updated 23w ago
Repository

About MCP Client-Server

MCP Client-Server is a Python and Golang example of MCP client-server architecture over HTTP. It is aimed at developers learning the pattern and includes a remote server and a client that calls a tool.

Key features

  1. 01Demonstrates MCP client-server architecture
  2. 02Serves remotely over HTTP
  3. 03Includes a client tool-call example

Use cases

  1. 01Learn MCP communication over HTTP
  2. 02Test tool calls to a remote server

MCP support

The project demonstrates an MCP server and client communicating over HTTP. The server is available at http://0.0.0.0:8000/mcp by default, and the client calls its tool.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttp://0.0.0.0:8000/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

MCP Client-Server

The simplest example of MCP client-server architecture.

The server can be run as a remote MCP server serving HTTP requests.

Client consumes the remote server over HTTP.

Commands

One-time setup

# Setup virtualenv
python3 -m venv venv
source venv/bin/activate

# Download all dependencies using uv
uv install

First, activate the virtual environment:

source venv/bin/activate

Then proceed with the following:

  1. Start mcp server in dev mode to test out tools
mcp dev server.py
  1. Run the MCP server
python server.py

Accessible at http://0.0.0.0:8000/mcp by default

  1. Run the MCP client that calls a tool on server
python client.py

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.