This MCP server exposes LinkedIn Ads data via the CData JDBC Driver in a local, read-only MCP interface. Once the server is running, you can use an MCP-compatible client (for example Claude Desktop) to query live LinkedIn Ads data without writing SQL. The server provides tools to inspect the data source and run queries through a simple JSON-RPC style interface. Typical operations involve discovering available tables (or entities), listing table columns, and executing SELECT queries against the LinkedIn Ads data source. Tools are named using the configured server name (e.g., linkedin-ads_get_tables, linkedin-ads_get_columns, linkedin-ads_run_query) and return results in CSV for tabular data.

Prerequisites:

• Java Development Kit (JDK 8 or newer) and a Java runtime
• Maven for building the MCP server
• Access to the CData JDBC Driver for LinkedIn Ads (downloadable from CData)

Installation steps:

1. Clone the repository git clone https://github.com/cdatasoftware/linkedin-ads-mcp-server-by-cdata.git cd linkedin-ads-mcp-server-by-cdata

2. Build the MCP server JAR mvn clean install

   This creates CDataMCP-jar-with-dependencies.jar in the target directory

3. Download and install the CData JDBC Driver for LinkedIn Ads from: https://www.cdata.com/drivers/linkedinads/download/jdbc

4. Place the generated LinkedIn Ads PRP configuration file (linkedin-ads.prp) that you create against your JDBC setup in an accessible path.

5. Run the MCP server java -jar /path/to/CDataMCP-jar-with-dependencies.jar /path/to/linkedin-ads.prp

Notes:

• The server runs on stdio, so it is intended for local clients on the same machine.
• Ensure the JDBC driver is licensed and properly configured in the PRP file (DriverPath, DriverClass, JdbcUrl, etc.).

Tips and known considerations:

• This is a read-only MCP server by design; write/update/delete operations are not exposed.
• Ensure your CLAUDE or other MCP client is restarted after adding or updating the server configuration so the new server appears.
• The PRP file (linkedin-ads.prp) must contain valid JDBC connection properties including Prefix, ServerName, ServerVersion, DriverPath, DriverClass, and JdbcUrl.
• If using OAuth connections, you may need to complete the authentication flow in a browser during the first connection test.
• For troubleshooting, verify that the Java process can access the JDBC driver jar and that the path to the PRP file is correct.