home / mcp / veeva mcp server

Veeva MCP Server

This read-only MCP Server allows you to connect to Veeva data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-veeva-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/veeva.prp"
      ]
    }
  }
}

You learn how to run a local MCP server that exposes live Veeva data to language models. This server is read-only and lets you query Veeva-supported data via natural language without writing SQL. It wraps the CData JDBC Driver and exposes data through an MCP interface, so you can ask questions and get current results from your Veeva source.

How to use

Use a compatible MCP client to connect to the local MCP server. The server runs on your machine and communicates via standard IO, so you can start it from your local environment and point your client at the same host.

Once started, you can ask questions like: “What is the latest status of my open opportunities?” or “Show me recent calendar events for today.” The server exposes a small set of tools that let you retrieve tables, list columns, and run queries against the Veeva data source. You do not need to write SQL queries to get live results; the MCP client handles translating your natural language requests into the appropriate data operations.

How to install

Prerequisites you need before starting the server:

Java Runtime Environment (JRE) or Java Development Kit (JDK) to run the MCP server JAR.

Maven to build the MCP server JAR from source.

A local Veeva data source accessible via the CData JDBC Driver for Veeva, including a valid license for the driver if required.

Additional configuration and usage notes

Build and run the MCP server from your workstation using the commands shown below. The server uses stdio, so you run it on the same machine as your MCP client.

1) Build the server JAR from source.

mvn clean install

2) Prepare the JDBC driver and connection string file for Veeva as described in the setup steps you follow locally. Ensure you have a veeva.prp file that contains your JDBC configuration, including the DriverPath, DriverClass, and JdbcUrl.

3) Run the MCP server with the prepared veeva.prp. The runtime command is shown here as the explicit start command.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/veeva.prp

Troubleshooting

If you cannot see the MCP server in your client, fully quit the client application and restart it. Ensure the veeva.prp file is accessible and correctly configured with your JDBC connection string.

If the client cannot retrieve data, verify the connection string and driver setup. Use the connection utility to test and copy the connection string into veeva.prp.

License

This MCP server is licensed under the MIT License. You may use, modify, and distribute it in accordance with the MIT terms.

Tools & Endpoints

The MCP server provides a small set of tools for data discovery and querying. You can use these to explore available data and run queries against the Veeva data source.

JSON-RPC Request Examples

Direct JSON-RPC requests are supported by clients that invoke the server tools. Use the following tool names to perform common tasks.

Notes on usage with Claude Desktop

Configure your Claude Desktop to include the MCP server by adding an MCP entry that points to the local java process and the veeva.prp configuration. Run Claude Desktop and refresh to discover the new MCP server.

Available tools

veeva_get_tables

Retrieves the list of tables available in the data source. The output is in CSV format with column headers in the first line.

veeva_get_columns

Retrieves the list of columns for a specified table. The output is in CSV format with column headers in the first line.

veeva_run_query

Executes a SQL SELECT query against the data source and returns the result set.