Servers
R
Run Sql Connectorx
@gigamori
An MCP server that executes SQL via ConnectorX and streams the result to a CSV or Parquet file. Supports PostgreSQL, MariaDB, BigQuery, RedShift, MS SQL Server, etc.
Overview
What is Run Sql Connectorx?
Run Sql Connectorx is an MCP server that uses ConnectorX to execute SQL queries against supported databases and return results as CSV or Parquet files. It is designed for MCP clients that need to run SQL and exchange data efficiently via files instead of inline payloads.
How to use Run Sql Connectorx?
Install via uvx and invoke with the required --conn <connection_token> option. Optionally set --csv-token-threshold <int> to enable per‑line CSV token counting. The server returns the string "OK" on success or "Error: <message>" on failure.
Key features of Run Sql Connectorx
- Efficient streaming via Arrow RecordBatch chunks
- Token-efficient file-based data exchange for MCP
- Cross-database support through ConnectorX
- Robust I/O: CSV headers, Parquet validation, error cleanup
- Output formats: CSV (UTF‑8) and Parquet (PyArrow defaults)
Use cases of Run Sql Connectorx
- Run SQL queries against PostgreSQL, MySQL, SQLite, or BigQuery
- Export large query results as CSV or Parquet for downstream analysis
