StarRocks

Executes SELECT queries and read-only operations against StarRocks databases through the MCP protocol, returning structured result sets with automatic connection pooling and error handling. The implementation maintains a persistent global connection to avoid repeated connection overhead while supporting query timeouts and result formatting for AI assistant consumption.

Executes data modification operations (INSERT, UPDATE, DELETE, CREATE TABLE, ALTER TABLE, DROP) against StarRocks through MCP tools with automatic transaction handling and schema change propagation. The implementation validates write operations before execution and clears the in-memory overview cache to ensure subsequent reads reflect schema/data changes.

Exposes database and table metadata through MCP resource URIs (starrocks:///databases, starrocks:///{db}/tables, starrocks:///{db}/{table}/schema) that AI assistants can reference directly without tool calls. The implementation translates URI paths into SHOW/DESCRIBE queries and caches results to avoid repeated metadata queries, enabling efficient schema discovery in multi-turn conversations.

Generates comprehensive summaries of tables and databases including schema definitions, row counts, and representative data samples through table_overview and db_overview tools. The implementation executes SHOW CREATE TABLE, COUNT(*), and LIMIT sampling queries, then caches results using (database_name, table_name) tuples to avoid redundant metadata/sampling queries across multiple AI assistant requests.

Executes a SQL query and automatically generates interactive Plotly charts from the result set through the query_and_plotly_chart tool. The implementation detects numeric and categorical columns, infers appropriate chart types (bar, line, scatter, pie), and returns both raw query results and embedded Plotly JSON for rendering in AI assistant interfaces or web frontends.

Exposes StarRocks internal metrics, system state, and performance information through proc:// URI resources (similar to Linux /proc filesystem), allowing AI assistants to query system tables and internal state without direct SQL access. The implementation translates proc:// paths into queries against StarRocks system tables (information_schema, sys database) and caches results to avoid repeated system queries.

Implements the Model Context Protocol (MCP) server specification to expose all StarRocks capabilities (tools and resources) to AI assistants in a standardized, protocol-compliant manner. The implementation handles MCP request/response serialization, tool schema definition, resource URI routing, and error handling according to MCP specification, enabling seamless integration with Claude, ChatGPT, and other MCP-compatible AI platforms.

Manages a global persistent database connection to StarRocks with automatic reconnection on failure, avoiding connection overhead for rapid-fire queries from AI assistants. The implementation maintains a single connection object at the module level, implements reconnection logic with exponential backoff, and provides connection reset functionality for error recovery without requiring AI assistant awareness of connection state.

Configures all StarRocks connection parameters and MCP server settings through environment variables (STARROCKS_HOST, STARROCKS_PORT, STARROCKS_USER, STARROCKS_PASSWORD, STARROCKS_DATABASE, MCP_PORT, etc.), enabling deployment flexibility without code changes. The implementation reads environment variables at server startup and validates required parameters, supporting both local development and containerized/cloud deployments with standard credential injection patterns.