snippy

snippy

3.5

If you are the rightful owner of snippy and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Snippy is a serverless code snippet management service using Azure Functions, Durable Functions, Azure OpenAI, Microsoft Fabric, and Azure AI Agents.

Snippy is an Azure Functions-based reference application that transforms any function into an MCP (Model Context Protocol) tool, consumable by GitHub Copilot Chat and other MCP-aware clients. It is designed as a production-style code-snippet service with AI-powered analysis. Snippy allows users to save code snippets, perform semantic retrieval using vector search, and generate language-specific code style guides or comprehensive wiki documentation from stored snippets. The application integrates with Microsoft Fabric and supports large-scale processing through Durable Functions. It is equipped with a reproducible infrastructure setup using the Azure Developer CLI (azd), enabling quick deployment of the entire stack, including Functions, Cosmos DB, Azure OpenAI, and Azure AI Agents.

Features

  • Remote MCP trigger – expose Functions as real-time SSE tools
  • AI-assisted documentation – 'deep-wiki' and 'code-style' agents create rich Markdown
  • Vector search on Cosmos DB DiskANN – low-latency semantic retrieval
  • One-click deploy – 'azd up' provisions and deploys code & infra
  • Codespaces & Dev Containers – fully configured dev environment in your browser or local VS Code

Tools

  1. save_snippet

    Save code snippets with vector embeddings for semantic search

  2. get_snippet

    Retrieve previously saved code snippets by their unique name

  3. code_style

    Generate language-specific code style guides from saved snippets

  4. deep_wiki

    Create comprehensive wiki documentation by analyzing code snippets