home / mcp / bing ads mcp server
This read-only MCP Server allows you to connect to Bing Ads 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/).
Configuration
View docs{
"mcpServers": {
"cdatasoftware-bing-ads-mcp-server-by-cdata": {
"command": "java",
"args": [
"-jar",
"/PATH/TO/CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/bing-ads.prp"
]
}
}
}This MCP server wraps the CData JDBC Driver for Bing Ads and presents live Bing Ads data through a simple MCP interface. You can query tables, inspect columns, and run read-only SQL-like queries from your AI client without writing SQL themselves. It runs locally and is designed for quick, read-only data access from Bing Ads.
You will run the MCP server on your machine and connect your MCP client (such as Claude Desktop) to it. The server exposes tools that let you discover available data and fetch query results. Use natural language prompts to ask questions like which campaigns are performing best, which ads have the highest click-through rates, or how your Bing Ads data is structured. The client will invoke the exposed tools behind the scenes, so you don’t need to write SQL.
Key tools you can use include retrieving the list of tables, listing columns for a table, and executing a read-only query. The tools are named using the server identifier (bingads) followed by a suffix, for example bingads_get_tables, bingads_get_columns, and bingads_run_query. Use these through your MCP client to explore and read data. Use the client’s natural language features to compose queries or ask for summaries of your data.
Prerequisites: Java runtime environment installed on your machine. You will also need the CData JDBC Driver for Bing Ads installed and licensed on the same machine.
Step-by-step commands to set up the MCP server locally:
# 1) Build the MCP server package
mvn clean install
# 2) Ensure the CData JDBC Driver for Bing Ads is downloaded and licensed on your machine
# 3) Create a properties file for the JDBC connection (bing-ads.prp) as described in the setup steps
# 4) Run the MCP server locally (stdio mode) using the final start command
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/bing-ads.prp
```},If you already have a ready bing-ads.prp configuration prepared, you can start the server with the exact path to that file in place of /PATH/TO/bing-ads.prp.
The server runs in stdio mode, meaning it is intended for use with clients that run on the same machine. Ensure your MCP client is configured to connect to the local stdio endpoint and that the bingads server is started before you attempt queries.
Configuring Claude Desktop or another MCP client involves registering a local stdio MCP server with the following runtime command and arguments. The client will load bing-ads.prp to establish the data connection.
{
"mcpServers": {
"bingads": {
"command": "java",
"args": [
"-jar",
"/PATH/TO/CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/bing-ads.prp"
]
}
}
}
````}],If you need to update the connection, edit bing-ads.prp with the correct DriverPath, DriverClass, and JdbcUrl, then restart the MCP server so the changes take effect.
If the MCP server does not appear in your client, ensure you have fully exited and re-opened the client after starting the server. Verify that the bing-ads.prp file is accessible and properly formatted. Check that the JDBC driver is licensed and reachable at the specified DriverPath.
If data cannot be retrieved, confirm the JDBC connection string in bing-ads.prp is correct and that any OAuth authentication requirements are completed in the browser during setup. If you encounter license or connectivity issues, contact CData Support.
This MCP server is designed for read-only access to Bing Ads data via the CData JDBC Driver. If you need full read-write capabilities and more advanced management features, consider an alternative MCP server configuration that supports those actions.
In the Bing Ads MCP server, the following tools are available. Each tool executes against the Bing Ads data source through the MCP interface.
Retrieves a list of available tables in the Bing Ads data source. The output is returned in CSV format with column headers on the first line.
Retrieves a list of columns for a specified table. The output is returned in CSV format with column headers on the first line.
Executes a SQL SELECT query against the Bing Ads data source and returns the result set.