MCP Example

@iddv

Basic information

About MCP Example

A reference implementation of the Model Context Protocol (MCP) enabling seamless tool calling between LLMs and applications. Features client/server architecture with HTTP APIs, local CLI execution, and AWS Bedrock integration in a production-ready, extensible framework.

MCP Example config

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

{
  "mcpServers": {
    "mcp-example": {
      "command": "python",
      "args": [
        "examples/servers/minesweeper_server.py",
        "--transport",
        "http",
        "--port",
        "8000"
      ]
    }
  }
}

MCP Example tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

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

Overview

What is Model Context Protocol (MCP) Example?

Model Context Protocol (MCP) Example is a repository of example servers and clients for building MCP-based AI applications, featuring a living Minesweeper game server as a showcase. Powered by FastMCP 2.0, it provides templates, educational resources, and enterprise features such as multiple transport protocols, session management, and OAuth 2.0 authentication. It is intended for developers who want to learn how to create sophisticated MCP servers or integrate them into production systems.

How to use Model Context Protocol (MCP) Example?

Clone the repository and install dependencies using Poetry (poetry install) or pip (pip install -e .). Start the Minesweeper server in development mode with mcp dev examples/servers/minesweeper_server.py or as an HTTP server with python examples/servers/minesweeper_server.py --transport http --port 8000. For production, configure transport via mcp.run(transport="streamable-http") or mcp.run(transport="websocket"). Test servers interactively using mcp dev or programmatically with the built-in testing module.

Key features of Model Context Protocol (MCP) Example

Living Minesweeper example demonstrating AI logical reasoning
Multiple transport protocols: stdio, HTTP, WebSocket
Session management for concurrent game instances
OAuth 2.0 authentication ready
Real-time data streaming and game state resources
Strategy guides, pattern library, and AI prompts

Use cases of Model Context Protocol (MCP) Example

Building interactive game servers with real-time state
Creating data processing servers that stream analysis results
Integrating external APIs through MCP tools and resources
Developing educational tools for teaching AI reasoning
Automating tasks with productivity-focused MCP servers

Frequently asked questions

What are the prerequisites for using Model Context Protocol (MCP) Example?

You need Python 3.10+ and either Poetry or pip for package management. FastMCP 2.0 is required and listed as a dependency.

How do I run the Minesweeper server?

Use `mcp dev examples/servers/minesweeper_server.py` for development mode with the MCP inspector, or start it as an HTTP server with `python examples/servers/minesweeper_server.py --transport http --port 8000`.

Can I use Model Context Protocol (MCP) Example with Claude Desktop?

Yes. Copy the configuration from `examples/configs/claude_desktop_config.json`, update the server paths, and restart Claude Desktop.

What transport protocols are supported?

The server supports stdio (default), HTTP (`streamable-http`), and WebSocket transports, chosen by the `--transport` argument or `mcp.run()` transport parameter.

What authentication mechanisms are available?

OAuth 2.0 is supported. Configure authorization URL, token URL, client ID, and scopes via the `@mcp.set_auth_config` decorator.

Comments

More Developer Tools MCP servers

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Meticulous

JiCo for Jira & Confluence – PII-redacting MCP server with Human-in-the-Loop

drkv-com

JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.