Skip to content
Back to search

snippy

🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search. Features orchestrated multi-agent workflows using OpenAI.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Azure-Samples/snippy with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Azure-Samples/snippy'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/azure-samples--snippy/badge.svg)](/listings/azure-samples--snippy)

HTML

<a href="/listings/azure-samples--snippy"><img src="/api/listings/azure-samples--snippy/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

* Azure subscription with permissions to create resources * [azd CLI](https://aka.ms/install-azd) installed * Choose your development environment: - **GitHub Codespaces** (fastest, no local setup required) - **VS Code Dev Containers** (requires [Docker Desktop](https://www.docker.com/products/docker-desktop)) - **Local development** (requires Python 3.11, Node 18+, Azure Functions Core Tools v4)

Deploy to Azure

**Using GitHub Codespaces:**

Click the "Open in GitHub Codespaces" badge above, then run:

azd auth login --use-device-code
azd up

**Using Dev Containers or Local Environment:**

azd init --template Azure-Samples/snippy
azd auth login
azd up

The `azd up` command will: * Prompt for an Azure region (recommend **eastus** or **swedencentral**) * Provision all resources (Functions, Cosmos DB, Azure OpenAI, DTS) * Create an Azure AD app registration for authentication * Deploy the application code

When complete, the Function App URL and MCP endpoint will be displayed. See the [tutorial](https://azure-samples.github.io/snippy/) for detailed instructions on local development, testing with emulators, and monitoring orchestrations.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 162 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <!--
  2. ---
  3. name: Snippy - Intelligent Code Snippet Service with MCP Tools
  4. description: A serverless code snippet management service using Azure Functions, Durable Functions, Azure OpenAI, Durable Functions and Agent Framework.
  5. page_type: sample
  6. languages:
  7. - python
  8. - bicep
  9. - azdeveloper
  10. products:
  11. - azure-functions
  12. - azure-durable-functions
  13. - azure-openai
  14. - azure-cosmos-db
  15. - azure-ai-projects
  16. - azure-ai-agents
  17. - fabric
  18. urlFragment: snippy
  19. ---
  20. -->
  21. <p align="center">
  22. <img src="https://raw.githubusercontent.com/Azure-Samples/snippy/main/images/snippy-logo.png" alt="Snippy">
  23. </p>
  24. [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://github.com/codespaces/new?hide_repo_select=true&ref=main&repo=Azure-Samples/snippy&machine=basicLinux32gb&devcontainer_path=.devcontainer%2Fdevcontainer.json)
  25. [![Open in Dev Containers](https://img.shields.io/static/v1?style=for-the-badge&label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/Azure-Samples/snippy)
  26. 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.
  27. ![Snippy Architecture](images/Snippy-Architecture-V2-L.png)
  28. 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.
  29. > **Important Security Notice**
  30. > This repository is intended for learning and demonstration purposes. **Do not** deploy it to production without a thorough security review. At a minimum you should:
  31. >
  32. > * Swap connection strings for **Managed Identity** + **Azure Key Vault**
  33. > * Restrict network access to Azure services via Private Endpoints or service‑tags
  34. > * Enable GitHub secret‑scanning and CI security tools
  35. [Features](#features) • [Lab Tutorial](#lab-tutorial) • [Getting Started](#getting-started) • [Guidance](#guidance)
  36. ---
  37. ## Features
  38. * **MCP Tool Integration** – expose Azure Functions as discoverable MCP tools for AI assistants
  39. * **Durable Agents with Microsoft Agent Framework** – build stateful AI agents using `ChatAgent` with automatic conversation history management
  40. * **Multi-Agent Orchestration** – coordinate specialized agents (DeepWiki, CodeStyle) using Durable Task Scheduler with fan-out/fan-in patterns
  41. * **Vector Search on Cosmos DB DiskANN** – semantic code retrieval using Azure OpenAI embeddings and low-latency vector indexing
  42. * **Monitoring & Observability** – track orchestrations in real-time using DTS dashboard (localhost:8082 local, Azure portal for cloud)
  43. * **One-click Deploy** – `azd up` provisions and deploys complete infrastructure including Functions, Cosmos DB, Azure OpenAI, and DTS
  44. * **Codespaces & Dev Containers** – fully configured development environment in your browser or local VS Code
  45. ### Tool Matrix
  46. | Tool Name | Purpose |
  47. | -------------------------------- | ------------------------------------------------------------------- |
  48. | `save_snippet` | Save code snippets with vector embeddings for semantic search |
  49. | `get_snippet` | Retrieve previously saved code snippets by their unique name |
  50. | `code_style` | Generate language-specific code style guides from saved snippets |
  51. | `deep_wiki` | Create comprehensive wiki documentation by analyzing code snippets |
  52. | `generate_comprehensive_documentation` | Orchestrate multi-agent workflow to produce deep wiki and style guide |
  53. ---
  54. ## Lab Tutorial
  55. New to Snippy? Start with our comprehensive **hands-on lab tutorial** that guides you through building the entire application from scratch:
  56. 📚 **[Snippy Tutorial: Building an AI-Enhanced Code Snippet Manager](https://azure-samples.github.io/snippy/)**
  57. The tutorial covers:
  58. * **Step-by-step implementation** – Build the complete application with detailed explanations
  59. * **Code review exercises** – Understand MCP tools, durable agents, and vector search patterns
  60. * **Local development** – Set up and test with Docker-based emulators
  61. * **Azure deployment** – Provision and deploy to production with azd
  62. * **Multi-agent orchestration** – Monitor complex workflows with DTS dashboard
  63. * **End-to-end testing** – Test with REST Client, GitHub Copilot, and MCP tools
  64. **Additional Resources:**
  65. * [Quick Reference](https://azure-samples.github.io/snippy/QUICK_REFERENCE/) – Essential commands and common tasks
  66. * [Troubleshooting Guide](https://azure-samples.github.io/snippy/TROUBLESHOOTING/) – Solutions to common issues
  67. Whether you're new to Azure Functions, MCP tools, or AI agent development, the lab provides a structured learning path with hands-on experience.
  68. ---
  69. ## Getting Started
  70. ### Prerequisites
  71. * Azure subscription with permissions to create resources
  72. * [azd CLI](https://aka.ms/install-azd) installed
  73. * Choose your development environment:
  74. - **GitHub Codespaces** (fastest, no local setup required)
  75. - **VS Code Dev Containers** (requires [Docker Desktop](https://www.docker.com/products/docker-desktop))
  76. - **Local development** (requires Python 3.11, Node 18+, Azure Functions Core Tools v4)
  77. ### Deploy to Azure
  78. **Using GitHub Codespaces:**
  79. Click the "Open in GitHub Codespaces" badge above, then run:
  80. ```bash
  81. azd auth login --use-device-code
  82. azd up
  83. ```
  84. **Using Dev Containers or Local Environment:**
  85. ```bash
  86. azd init --template Azure-Samples/snippy
  87. azd auth login
  88. azd up
  89. ```
  90. The `azd up` command will:
  91. * Prompt for an Azure region (recommend **eastus** or **swedencentral**)
  92. * Provision all resources (Functions, Cosmos DB, Azure OpenAI, DTS)
  93. * Create an Azure AD app registration for authentication
  94. * Deploy the application code
  95. When complete, the Function App URL and MCP endpoint will be displayed. See the [tutorial](https://azure-samples.github.io/snippy/) for detailed instructions on local development, testing with emulators, and monitoring orchestrations.
  96. ---
  97. ## Guidance
  98. ### Region Availability
  99. Azure OpenAI model support varies by region. Verify availability [here](https://learn.microsoft.com/azure/ai-services/openai/concepts/models#standard-deployment-model-availability) and choose the same region for all Azure resources. **eastus** and **swedencentral** are good default choices.
  100. ### Security
  101. Snippy uses User-Assigned Managed Identity for secure service-to-service authentication. The infrastructure is configured with:
  102. * **User-Assigned Managed Identity** on the Function App with appropriate RBAC roles:
  103. * Cosmos DB Data Contributor
  104. * Storage Blob Data Owner and Queue Data Contributor
  105. * Application Insights Monitoring Metrics Publisher
  106. * Azure AI Project Developer
  107. For production deployments, we recommend:
  108. * Restrict inbound traffic with Private Endpoints + VNet integration
  109. * Enable network security features like service endpoints and firewall rules
  110. ---
  111. ## Contributing
  112. Standard **fork → branch → PR** workflow. Use *Conventional Commits* (`feat:`, `fix:`) in commit messages.
  113. ---
  114. ## License
  115. MIT © Microsoft Corporation

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.