A lightweight MCP server that provides access to databases through ODBC using PyODBC, compatible with Virtuoso DBMS and any DBMS with ODBC drivers.

Installation

From source code

git clone https://github.com/OpenLinkSoftware/mcp-pyodbc-server.git
cd mcp-pyodbc-server

Prerequisites - uv installation

pip install uv

Prerequisites - uv via Homebrew

brew install uv

Configuration

Claude Desktop

{
  "mcpServers": {
    "my_database": {
      "command": "uv",
      "args": ["--directory", "/path/to/mcp-pyodbc-server", "run", "mcp-pyodbc-server"],
      "env": {
        "ODBC_DSN": "dsn_name",
        "ODBC_USER": "username",
        "ODBC_PASSWORD": "password",
        "API_KEY": "sk-xxx"
      }
    }
  }
}

ODBC DSN Configuration

[VOS]
Description = OpenLink Virtuoso
Driver = /path/to/virtodbcu_r.so
Database = Demo
Address = localhost:1111
WideAsUTF16 = Yes

Available Tools

Tool	Description
podbc_get_schemas	Get a list of database schemas available for the connected database management system (DBMS)
podbc_get_tables	Get a list of tables associated with the selected database schema
podbc_describe_table	Provide a description of a table, including column names, data types, null handling, auto-increment...
podbc_filter_table_names	Get a list of tables based on a substring pattern from the q field, associated with the selected database...
podbc_query_database	Execute an SQL query and return results in JSON format
podbc_execute_query	Execute an SQL query and return results in JSONL format
podbc_execute_query_md	Execute an SQL query and return results in Markdown table format
podbc_spasql_query	Execute a SPASQL query and return results (function specific to Virtuoso)
podbc_virtuoso_support_ai	Interaction with Virtuoso support assistant/agent for LLM interaction

Features

• Schema retrieval: Extract and output all schema names from the connected database
• Table retrieval: Extract table information for specific schemas or all schemas
• Table description: Generate detailed descriptions of table structure with column information, nullable attributes, primary and foreign keys
• Table search: Filter and retrieve tables based on name substrings
• Stored procedure execution: Execute stored procedures when connected to Virtuoso
• Query execution: Support for JSONL results format and Markdown table format
• SPASQL support: Execute hybrid SQL/SPARQL queries (specific to Virtuoso)
• AI assistant integration: LLM interaction capabilities specific to Virtuoso

Environment Variables

Required

• ODBC_DSN - ODBC data source name for connecting to the database
• ODBC_USER - Database username for authentication
• ODBC_PASSWORD - Database password for authentication

Optional

• API_KEY - API key for integration with AI services

Notes

ODBC driver setup and configuration is required. Compatible with Virtuoso DBMS and any DBMS with ODBC drivers. Includes MCP Inspector for troubleshooting: npm install -g @modelcontextprotocol/inspector and run with npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-pyodbc-server run mcp-pyodbc-server