Veeva MCP Server By Cdata

What is veeva-mcp-server-by-cdata?

veeva-mcp-server-by-cdata is a read-only Model Context Protocol (MCP) server built by CData that allows large language models (LLMs) like Claude Desktop to query live data from Veeva using natural language questions. It wraps the CData JDBC Driver for Veeva and exposes Veeva data as relational SQL models through a simple MCP interface.

How to use veeva-mcp-server-by-cdata?

Clone the repository, build with mvn clean install, install and license the CData JDBC Driver for Veeva, configure the connection string using the driver’s utility, create a .prp file with JDBC properties, then add the server to your Claude Desktop configuration by editing claude_desktop_config.json. Run or refresh Claude Desktop to start querying Veeva data.

Key features of veeva-mcp-server-by-cdata

• Read-only MCP server for Veeva data via natural language
• Uses CData JDBC Driver for Veeva as the underlying connector
• Exposes tools: get_tables, get_columns, and run_query (SELECT only)
• No SQL required – LLMs can ask questions directly
• Runs locally using stdio transport

Use cases of veeva-mcp-server-by-cdata

• Query Veeva data from Claude Desktop without writing SQL
• Answer business questions about Veeva records (e.g., “What is the correlation between closed won opportunities and account industry?”)
• Retrieve table and column metadata from Veeva for exploration