A lightweight MCP server that provides connectivity to ODBC databases through SQLAlchemy and pyodbc, compatible with Virtuoso DBMS and other database backends with SQLAlchemy providers.

Installation

From Source

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

Prerequisites

pip install uv
# or
brew install uv

Configuration

Claude Desktop

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

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 table description, including column names, data types, NULL handling, auto-increment...
podbc_filter_table_names	Get a list of tables matching a substring pattern associated with the selected database schema
podbc_query_database	Execute a SQL query and return results in JSONL format
podbc_execute_query	Execute a SQL query and return results in JSONL format
podbc_execute_query_md	Execute a SQL query and return results in Markdown table format
podbc_spasql_query	Execute a SPASQL query and return results
podbc_sparql_query	Execute a SPARQL query and return results
podbc_virtuoso_support_ai	Interact with Virtuoso support assistant/agent -- Virtuoso-specific interaction function...

Features

• Schema retrieval: fetch and display 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 structures with column names, data types, nullable attributes, primary and foreign keys
• Table search: filter and retrieve tables based on name substrings
• Stored procedure execution: in the case of Virtuoso, execute stored procedures and retrieve results
• Query execution: JSONL results format, optimized for structured responses
• Query execution: Markdown table format, ideal for reporting and visualization
• Multi-database system support: Virtuoso, PostgreSQL, MySQL, SQLite
• SPARQL and SPASQL query support for Virtuoso
• Integration with Virtuoso AI support assistant

Environment Variables

Required

• ODBC_DSN - ODBC data source name
• ODBC_USER - database username
• ODBC_PASSWORD - database password

Optional

• API_KEY - API key for AI services

Notes

Requires ODBC DSN configuration in ~/.odbc.ini and unixODBC runtime environment. Supports multiple database connection formats, including virtuoso+pyodbc://user:password@ODBC_DSN, postgresql://, mysql+pymysql://, and sqlite:///. For troubleshooting, install MCP Inspector using the command 'npm install -g @modelcontextprotocol/inspector'.