MCP Server

Model Context Protocol (MCP) is an open standard proposed by Anthropic in November 2024. It standardizes how large language models (LLMs) communicate with external systems (such as databases and APIs). Traditional AI integration requires a plugin tailored for each tool, which results in low development efficiency and poor compatibility. MCP uses standardized interfaces (similar to the USB protocol in the AI world) that allow LLMs to dynamically understand tool functions and perform operations. This significantly reduces integration costs.

DWS MCP Server provides a series of MCP-based tools and resources. It enables AI models and agents to seamlessly connect to DWS clusters and provides functions such as statement execution and metadata query. With large models, users can directly operate databases using natural languages. The system converts natural languages into SQL statements, which are used to query data. Then users can receive query results.

Precautions

This function is supported only by clusters running version 9.1.1.200 and later.

Capabilities Provided by DWS MCP Server

Metadata query: Use list_schemas, list_databases, and list_tables to list all schemas, databases, and tables, respectively. Use get_table_info and get_comment to obtain table/view definitions or comments.
Database activity monitoring: Use get_activity to query the pgxc_stat_activity view and obtain details about recent database jobs.
Statement execution: Use execute_query to execute specified statements.
System information acquisition: Use system:///{system_path} to obtain system information, such as version information (system:///version).