News
Microsoft's MCP Server Preview for Azure PostgreSQL To Streamline AI Integration
Microsoft on Thursday introduced a public preview of its new Model Context Protocol (MCP) Server for Azure Database for PostgreSQL, aimed at simplifying the process for AI models to interact with enterprise data.
The MCP Server supports integration between large language models and business data stored in Azure's PostgreSQL Flexible Server. Built on an open protocol, it eliminates the need for custom connectors by enabling AI applications to interact directly with APIs, services and external data sources using a common interface, according to Microsoft
"Think of it as a common language that enables AI assistants to establish two-way connections with external data sources and services," said Shreya R. Aithal, product manager at Microsoft. "It promotes interoperability by allowing diverse systems to work together seamlessly, supports scalable and secure integration with enterprise applications and data, and future-proofs these integrations, ensuring smooth transitions between different models or platforms."
The MCP Server enables natural language querying capabilities through supported development tools like Claude Desktop and Visual Studio Code. According to Microsoft, key features include:
- MCP Host: AI applications, agents, programs, or tools like Copilot Studio and Claude Desktop that seek to access data through MCP.
- MCP Client: An MCP Host includes an MCP client component responsible for connecting to one or more MCP servers and relaying information between the application's AI models and those servers.
- MCP Server: A lightweight program that interfaces with data sources, services or APIs and exposes the following standardized capabilities or actions to the MCP clients:
- Tools: Functions that can be invoked by AI models to fetch information or perform actions like sending a message or updating database records.
- Resources: Data, files or documents that a server exposes to the AI applications, providing a rich interface for applications and MCP servers to interact, beyond using text.
- Prompts: Pre-defined templates that an application user can request for effective AI interactions to accomplish specific tasks.
- Data sources, services and APIs: External systems with the data context required to enhance the AI models, which MCP servers can securely access.
Developers can access sample code, setup guides and instructional videos from the Azure-Samples GitHub repository, enabling immediate experimentation with the protocol.
Microsoft said it intends to add new features to the MCP Server in future releases and encouraged users to share feedback during the preview phase.