Overview
OpenLink MCP Server for ODBC via PyODBC is a lightweight MCP (Model Context Protocol) server built with FastAPI and pyodbc that provides MCP‑compliant access to ODBC‑enabled databases. It is designed to be compatible with Virtuoso and any other DBMS backend that offers an ODBC driver. The server exposes MCP tools to discover database schemas, list tables, and describe table structures including column names, data types, nullable attributes, and key constraints (primary/foreign). It also supports filtering tables by name substrings and retrieving comprehensive table metadata. When connected to Virtuoso, it can execute stored procedures and return results. For querying, it supports multiple output formats: JSONL for structured responses and Markdown tables for reporting. It includes Virtuoso‑specific features such as SPASQL query support and a Virtuoso AI assistant option. Configuration relies on ODBC DSNs, credentials, and an API key, with guidance for environment setup and troubleshooting via the MCP Inspector. Overall, the server enables MCP clients to interact with ODBC‑connected databases in a consistent, protocol‑driven manner.
Features
Get Schemas
Fetch and list all schema names from the connected database.
Get Tables
Retrieve table information for specific schemas or all schemas.
Describe Table
Generate a detailed description of table structures, including column names, data types, nullable attributes, and keys.
Search Tables
Filter and retrieve tables based on name substrings.
Execute Stored Procedures
When connected to Virtuoso, execute stored procedures and retrieve results.
Execute Queries
Execute SQL queries and return results in multiple formats: JSONL and Markdown table.
Who Is This For?
- Database developers:Use MCP client tools to query schemas, tables, and run SQL via ODBC.
- DBAs:Administrators using MCP to explore DB schemas, tables, and execute queries.
- Data engineers:Integrate ODBC-connected databases into MCP-enabled applications for data integration and reporting workflows.
