Frequently Asked Questions (FAQ) about UBOS MCP Server for ODBC

Q: What is an MCP Server? A: MCP (Model Context Protocol) is an open standard that simplifies how applications provide contextual information to Large Language Models (LLMs). An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools.

Q: What is ODBC? A: ODBC (Open Database Connectivity) is a standard API that allows applications to access data in a variety of database management systems (DBMS) using a unified interface.

Q: What does the UBOS MCP Server for ODBC do? A: The UBOS MCP Server for ODBC provides Large Language Models with transparent access to ODBC-accessible data sources. This allows AI Agents to query, analyze, and leverage data residing in various databases.

Q: What types of databases are supported? A: The MCP Server for ODBC supports any database that has an ODBC driver, including Virtuoso, MySQL, PostgreSQL, SQL Server, and many others.

Q: How do I install the MCP Server for ODBC? A: The installation process typically involves cloning the repository, installing dependencies using npm, and configuring environment variables (e.g., ODBC Data Source Name, username, password).

Q: What environment variables do I need to configure? A: You need to configure environment variables for the ODBC Data Source Name (ODBC_DSN), User (ODBC_USER), Password (ODBC_PASSWORD), and ODBC INI file (ODBCINI).

Q: What tools are provided by the MCP Server? A: The server provides tools such as get_schemas, get_tables, describe_table, filter_table_names, query_database, query_database_md, query_database_jsonl, spasql_query, sparql_query, and virtuoso_support_ai.

Q: What is get_schemas used for? A: get_schemas retrieves a list of all available schemas within the connected database.

Q: How does query_database work? A: query_database executes a standard SQL query and returns the results in JSON format.

Q: What is the purpose of query_database_md? A: query_database_md executes a standard SQL query and returns the results formatted as a Markdown table.

Q: What is SPASQL and how is it supported? A: SPASQL is a hybrid of SQL and SPARQL, used for querying both relational and semantic web data. The MCP Server supports SPASQL queries for Virtuoso databases.

Q: How can I use the virtuoso_support_ai tool? A: The virtuoso_support_ai tool leverages Virtuoso’s AI Assistant function, allowing you to interact with LLMs directly through the database.

Q: How do I configure Claude Desktop to use the MCP Server? A: You need to modify the claude_desktop_config.json file to include the command, arguments, and environment variables for the MCP Server.

Q: How do I configure Cline (Visual Studio Extension)? A: You need to modify the cline_mcp_settings.json file to include the command, arguments, and environment variables for the MCP Server.

Q: How do I use the MCP Server with Cursor? A: Use the Command + I or Control + I key combination to open the Chat Interface, select Agent, and enter your prompt using the @odbc pattern.

Q: Where can I find more information and usage examples? A: Refer to the documentation, which includes screencasts demonstrating basic usage with Claude Desktop, Cline, and Cursor.