snippy
🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search. Features orchestrated multi-agent workflows using OpenAI.
101stars
1,244forks
Python
Added 2/6/2026
AI Agentsai-agentsazure-functionscopilotcosmosdbdurable-functions
Installation
# Add to your Claude Code skills
git clone https://github.com/Azure-Samples/snippy<!--
---
name: Snippy - Intelligent Code Snippet Service with MCP Tools
description: A serverless code snippet management service using Azure Functions, Durable Functions, Azure OpenAI, Durable Functions and Agent Framework.
page_type: sample
languages:
- python
- bicep
- azdeveloper
products:
- azure-functions
- azure-durable-functions
- azure-openai
- azure-cosmos-db
- azure-ai-projects
- azure-ai-agents
- fabric
urlFragment: snippy
---
-->
<p align="center">
<img src="https://raw.githubusercontent.com/Azure-Samples/snippy/main/images/snippy-logo.png" alt="Snippy">
</p>
Snippy is an Azure Functions-based reference application that demonstrates how to build MCP (Model Context Protocol) tools that integrate with AI assistants like GitHub Copilot. It showcases a modern serverless AI application architecture where Azure Functions serve as both traditional APIs and MCP-compatible tools that AI assistants can discover and use.
The system uses Durable Task Scheduler to orchestrate multi-agent workflows, Cosmos DB with vector indexing for semantic code search, and Azure OpenAI for embeddings and LLM capabilities. The project ships with reproducible azd infrastructure—azd up deploys the entire stack and works with both local Docker-based emulators and Azure cloud services.