Snippy
🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search. Features orchestrated multi-agent workflows using OpenAI.
What is Snippy?
Snippy is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🧩 build ai-powered mcp tools with azure functions, durable agents & cosmos vector search. features orchestrated multi-agent workflows using openai.
🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search. Features orchestrated multi-agent workflows using OpenAI.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🧩 Build AI-powered MCP Tools with Azure Functions, Durable A
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx snippyConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Snippy
Snippy is an Azure-native MCP server sample that demonstrates how to build AI-powered MCP tools on top of Azure Functions, Durable Task Scheduler, Cosmos DB with vector indexing, and Azure OpenAI. It exposes five MCP-compatible tools — save_snippet, get_snippet, code_style, deep_wiki, and generate_comprehensive_documentation — that let AI assistants save code snippets with semantic embeddings, retrieve them by name, infer coding style guides, and produce multi-agent orchestrated documentation. Developers use it as a production-grade reference architecture for building scalable, serverless MCP tool backends on Azure.
Prerequisites
- An Azure subscription with permissions to create resource groups, Azure OpenAI, Cosmos DB, Functions, and Storage accounts
- Azure Developer CLI (azd) installed (https://aka.ms/azd-install)
- Python 3.11 or higher and Node.js 18 or higher for local development
- Azure Functions Core Tools v4 for local testing
- An MCP-compatible client such as Claude Desktop or GitHub Copilot
Initialize the project with azd
Use the Azure Developer CLI to initialize and authenticate. You can start from GitHub Codespaces, a Dev Container, or a local environment.
azd init --template Azure-Samples/snippy
azd auth loginDeploy to Azure
Run azd up to provision all required Azure resources (Azure OpenAI, Cosmos DB with vector indexing, Azure Functions, Durable Task Scheduler, Storage). When prompted, select eastus or swedencentral for Azure OpenAI availability.
azd upNote the deployed MCP endpoint
After deployment completes, azd will output the URL of your hosted MCP server. Copy this endpoint — you will use it to configure your MCP client.
Configure your MCP client
Add the Snippy MCP server endpoint to your MCP client configuration. Because Snippy runs as a hosted Azure Function, no local command is needed — use the HTTP transport with your deployed endpoint.
{
"mcpServers": {
"snippy": {
"command": "npx",
"args": ["snippy"],
"env": {
"SNIPPY_ENDPOINT": "https://your-snippy-app.azurewebsites.net/api"
}
}
}
}Test the tools
Ask your AI assistant to save a code snippet, then retrieve it by name to verify Cosmos DB vector search is working. Try the deep_wiki tool on a snippet to see multi-agent Durable Task orchestration in action.
Snippy Examples
Client configuration
Example MCP client configuration for the deployed Snippy Azure Functions endpoint.
{
"mcpServers": {
"snippy": {
"command": "npx",
"args": ["snippy"],
"env": {
"SNIPPY_ENDPOINT": "https://your-snippy-app.azurewebsites.net/api"
}
}
}
}Prompts to try
These prompts exercise all five MCP tools exposed by Snippy.
- "Save this Python function as a snippet named 'retry_decorator': [paste your code]"
- "Retrieve the snippet named 'retry_decorator'"
- "Generate a coding style guide based on all my saved Python snippets"
- "Create comprehensive wiki documentation for the snippets in my collection"
- "What snippets do I have related to database connection handling?"Troubleshooting Snippy
azd up fails with 'Azure OpenAI not available in this region'
Select eastus or swedencentral when azd prompts for a region during deployment. Azure OpenAI model availability is region-specific and these regions have the broadest coverage.
Vector search returns no results even after saving snippets
Cosmos DB vector indexing may take a few minutes to index new documents after first ingestion. Wait 2-3 minutes after saving snippets before querying. Also verify that the Azure OpenAI embeddings model was deployed successfully in the azd output.
Permission denied errors when the Functions app writes to Cosmos DB
Snippy uses User-Assigned Managed Identity with RBAC. Ensure that the azd deployment completed fully and that the identity was granted Cosmos DB Data Contributor and Storage Blob Data Contributor roles. Re-running 'azd up' will re-apply role assignments.
Frequently Asked Questions about Snippy
What is Snippy?
Snippy is a Model Context Protocol (MCP) server that 🧩 build ai-powered mcp tools with azure functions, durable agents & cosmos vector search. features orchestrated multi-agent workflows using openai. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Snippy?
Follow the installation instructions on the Snippy GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Snippy?
Snippy works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Snippy free to use?
Yes, Snippy is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Snippy Alternatives — Similar Coding Agents Servers
Looking for alternatives to Snippy? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Snippy in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Snippy?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.