Back to Home
microsoft icon

mcp-for-beginners

by microsoft

Overview

Building custom Model Context Protocol (MCP) servers for AI agent development, including weather data retrieval and GitHub repository automation.

Installation

Run Command
PORT=3001 python src/__init__.py sse

Environment Variables

  • LOG_LEVEL
  • PORT
  • AZURE_OPENAI_CHAT_DEPLOYMENT_NAME
  • AZURE_OPENAI_API_KEY
  • AZURE_OPENAI_ENDPOINT
  • AZURE_OPENAI_API_VERSION
  • GITHUB_TOKEN

Security Notes

The server includes tools that execute system commands (`git clone`, `open_in_vscode`) based on user input. Specifically, the `open_in_vscode` tool on Windows uses `subprocess.run` with `shell=True` which is a critical security vulnerability if the `folder_path` contains malicious shell metacharacters, potentially leading to arbitrary code execution. There is no explicit input validation for URL formats or paths within the `git_clone_repo` and `open_in_vscode` tools themselves, relying on external command failures, which is not robust enough for untrusted inputs. However, no hardcoded secrets or direct `eval` calls were found in the provided server code snippets.

Similar Servers

Stats

Interest Score100
Security Score5
Cost ClassLow
Stars14083
Forks4613
Last Update2026-01-19

Tags

MCPAI ToolkitVS Code ExtensionPythonAI AgentToolsGitHub AutomationWeather ServiceDebuggingLLM Integration