一款模型上下文协议（MCP）服务器，使AI代理能够通过自然语言查询与Azure Cosmos数据库交互。具备企业级安全功能，包括Azure Entra ID认证、文档操作、矢量搜索、混合搜索和模式发现。

🎯 为什么要用这个工具包？

问题所在： 构建能够安全访问Cosmos数据库企业数据的AI代理，需要在MCP协议、认证、嵌入服务和云安全方面具备深厚专业知识。这过程复杂、耗时且容易出错。

解决方案： 该工具包提供了一个生产准备、全自动化的MCP服务器，能够处理所有事务：

• ✅ MCP 协议 — 无需协议知识;我们负责所有 MCP 合规性
• ✅ Enterprise Security — Azure Entra ID + Managed Identity + RBAC built-in
• ✅ Vector & Hybrid Search — Azure OpenAI/Foundry 的自动嵌入
• ✅ 一键部署 — 只需一键即可在几分钟内部署到 Azure
• ✅ 模式发现 — AI代理自动理解您的数据
• ✅ 生产准备 — 自动扩展、监控和企业级托管

5分钟后开始： ⚡ 快速入门指南

Azure Cosmos DB MCP Toolkit

A Model Context Protocol (MCP) server that enables AI agents to interact with Azure Cosmos DB through natural language queries. Features enterprise-grade security with Azure Entra ID authentication, document operations, vector search, hybrid search, and schema discovery.

🎯 Why Use This Toolkit?

The Problem:
Building AI agents that can securely access enterprise data in Cosmos DB requires deep expertise in MCP protocol, authentication, embedding services, and cloud security. It’s complex, time-consuming, and error-prone.

The Solution:
This toolkit provides a production-ready, fully automated MCP server that handles everything:

• ✅ MCP Protocol — No protocol knowledge needed; we handle all MCP compliance
• ✅ Enterprise Security — Azure Entra ID + Managed Identity + RBAC built-in
• ✅ Vector & Hybrid Search — Automatic embeddings with Azure OpenAI/Foundry
• ✅ One-Click Deployment — Deploy to Azure in minutes with a single button click
• ✅ Schema Discovery — AI agents automatically understand your data
• ✅ Production-Ready — Auto-scaling, monitoring, and enterprise-grade hosting

Get started in 5 minutes: ⚡ Quick Start Guide

See it in action: 📚 Real-world use cases • 🗺️ Roadmap • 🤝 Contributing

Prerequisites

• Azure subscription (Free account)
• Azure Cosmos DB account (Create account)
• Embedding Service (one of the following for vector search and hybrid search):
  • Azure AI Services (Cognitive Services) with embedding model (Create)
  • Azure AI Foundry with embedding model (Create)
  • OpenAI API with API key (Get API key)
• Azure CLI (Install) installed and authenticated
• PowerShell 7+ (Install) (for deployment scripts)
• Docker Desktop (Install) installed and running
• .NET 9.0 SDK (Install) (for local development)
• Git (Install)