mcp-python-starter
Verified Safeby SamMorrowDrums
Overview
A starter template for developing Model Context Protocol (MCP) servers in Python, demonstrating core MCP features and patterns.
Installation
uv run mcp-python-starterEnvironment Variables
- LLM_API_KEY
Security Notes
The server includes dynamic tool loading and LLM sampling functionality, which inherently involve dynamic code execution and external LLM calls. While the provided code handles these within the context of the MCP framework, robust input validation and careful consideration of LLM outputs are crucial in a production environment. No direct `eval()` or unvalidated `subprocess` calls were identified in the truncated code that would allow arbitrary code execution by a user.
Similar Servers
mcp-server-python-template
This server acts as a template for building Model Context Protocol (MCP) servers in Python, specifically demonstrating how to expose weather-related tools (get_alerts, get_forecast) by integrating with an external API (National Weather Service) to provide context and actions for AI models.
mcp-go-starter
A feature-complete Model Context Protocol (MCP) server template in Go, demonstrating tools, resources, and prompts for AI agent interaction.
agents-mcp-usage
This repository demonstrates the integration of a Model Context Protocol (MCP) server with various AI agent frameworks, showcasing agent communication and operation within a shared context.
mcp_server
This server template provides a foundation for building Model Context Protocol (MCP) servers to integrate with AI assistants and other MCP clients, offering tools for GitHub, Microsoft Graph, weather data, and JWT decoding.