run-sql-connectorx

Executes SQL queries against 8+ database backends (PostgreSQL, MariaDB, BigQuery, MS SQL Server, Redshift, MySQL, SQLite, Oracle) through ConnectorX's Rust-based connector abstraction layer. ConnectorX handles connection pooling, query compilation, and result streaming without materializing full result sets in memory, enabling efficient execution of large queries. The MCP tool wraps ConnectorX's query API to expose database execution as a standardized Model Context Protocol resource.

Streams SQL query results directly to CSV or Parquet files without buffering the full result set in memory. Uses ConnectorX's columnar data model to write results in batches, enabling efficient export of multi-gigabyte datasets. The streaming approach prevents out-of-memory errors on large queries and allows results to be consumed incrementally by downstream tools or LLM context windows.

Wraps the SQL execution and result export functionality as an MCP (Model Context Protocol) tool named 'run_sql', exposing database queries as a standardized resource that Claude, Cline, and other MCP-compatible clients can invoke. The MCP server handles request/response serialization, error handling, and result streaming through the MCP transport layer, abstracting database connection management from the client.

Executes SQL queries with parameter binding to prevent SQL injection attacks. The implementation accepts query strings with placeholders (e.g., '?' or ':param') and separate parameter values, passing both to ConnectorX's query execution layer which handles safe parameter substitution at the database driver level. This prevents untrusted input (from LLM outputs or user input) from being interpreted as SQL code.

Manages database connections through ConnectorX's connection pooling layer, which reuses connections across multiple queries to reduce connection overhead. The MCP server maintains connection state and handles connection lifecycle (creation, reuse, cleanup) transparently. Pooling is configured implicitly based on ConnectorX defaults, with connection timeouts and retry logic handled by the underlying database driver.

Captures database errors (connection failures, syntax errors, permission errors, timeouts) from ConnectorX and translates them into MCP error responses with human-readable messages. The implementation preserves database-specific error codes and context while sanitizing sensitive information (e.g., internal server details). Errors are returned to the MCP client with appropriate HTTP-like status codes and error descriptions.