mcp-odbc-server logo

mcp-odbc-server

by OpenLinkSoftware

The mcp-odbc-server provides Large Language Models with transparent access to ODBC-accessible data sources via a Data Source Name configured for a specific ODBC Connector. It is a generic ODBC server for the Model Context Protocol (MCP).

View on GitHub

Last updated: N/A

What is mcp-odbc-server?

The mcp-odbc-server is a TypeScript layer built on top of node-odbc that acts as an MCP server, routing calls to the host system's local ODBC Driver Manager via node.js. It enables LLMs to interact with databases through ODBC connections.

How to use mcp-odbc-server?

To use the mcp-odbc-server, you need to install the prerequisites (node.js, MCP components), clone the repository, install dependencies, configure environment variables for database connection details (DSN, user, password), and then start the server. Client applications like Claude Desktop, Cline (Visual Studio Extension), and Cursor can then be configured to use the server by providing the server's command and arguments in their respective configuration files.

Key features of mcp-odbc-server

  • Provides transparent access to ODBC-accessible data sources for LLMs

  • Supports various ODBC Connectors

  • Includes tools for schema and table discovery (get_schemas, get_tables, describe_table, filter_table_names)

  • Enables SQL query execution (query_database, execute_query, execute_query_md)

  • Supports SPASQL and SPARQL query execution (spasql_query, sparql_query)

  • Offers Virtuoso-specific AI assistant integration (virtuoso_support_ai)

Use cases of mcp-odbc-server

  • Enabling LLMs to query and analyze data stored in relational databases

  • Building AI-powered applications that leverage data from ODBC data sources

  • Integrating LLMs with existing database systems for data retrieval and manipulation

  • Providing a standardized interface for LLMs to access different database systems via ODBC

FAQ from mcp-odbc-server

What is MCP?

MCP stands for Model Context Protocol. It's a protocol that allows LLMs to interact with external tools and services.

What databases are supported?

The server supports any database accessible via ODBC. The documentation focuses on Virtuoso, but other databases can be used.

What are the prerequisites for installation?

You need to have node.js (version 21.1.0 or higher), npm, and the necessary MCP components installed.

How do I configure the database connection?

You need to set the ODBC_DSN, ODBC_USER, and ODBC_PASSWORD environment variables in the .env file.

How do I test the installation?

You can use the MCP Inspector to connect to the server and test the available tools.