snippy
Verified Safeby Azure-Samples
Overview
An AI-powered serverless code snippet manager that uses Azure Functions as MCP tools for AI assistants like GitHub Copilot, leveraging vector search and multi-agent orchestration for documentation and style guide generation.
Installation
cd src && func startEnvironment Variables
- AZURE_OPENAI_ENDPOINT
- EMBEDDING_MODEL_DEPLOYMENT_NAME
- AGENTS_MODEL_DEPLOYMENT_NAME
- COSMOS_ENDPOINT
- COSMOS_DATABASE_NAME
- COSMOS_CONTAINER_NAME
- TASKHUB_NAME
- DTS_CONNECTION_STRING
Security Notes
The project follows strong security practices for Azure cloud environments, utilizing Azure Managed Identity (User-Assigned) and Azure AD authentication (`DefaultAzureCredential`) for service-to-service communication. Azure CLI login provides local development authentication without hardcoding secrets. The `setup-app-registration.sh` script dynamically configures an Azure AD application and pre-authorizes GitHub Copilot. The README explicitly advises thorough security review for production, recommending Key Vault, Private Endpoints, and network restrictions. No 'eval' or obvious obfuscation found.
Similar Servers
klavis
Creates an AI agent that uses Klavis Strata to interact with Gmail and YouTube through MCP, demonstrating how to summarize a YouTube video and email the summary.
mcp-server-azure-devops
This server provides an AI agent with tools to interact with Azure DevOps services, including searching code, wikis, and work items, managing pull requests, retrieving project details, and handling pipeline operations.
remote-mcp-functions-typescript
Provides a remote Model Context Protocol (MCP) server implemented with Azure Functions in TypeScript, enabling AI agents like GitHub Copilot to interact with custom tools and data storage.
mcpc
A framework for building agentic Model Context Protocol (MCP) servers by composing existing MCP tools. It enables the creation of portable, interoperable AI agents with flexible execution modes and robust logging/tracing capabilities.