Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Data and BI - official IBM server

IBM watsonx.data MCP server

MCP server for IBM watsonx.data lakehouses with tools for instance status, Presto and Spark engines, catalog and schema exploration, SQL query execution, Spark applications and data ingestion. It runs locally from ibm-watsonxdata-mcp-server (pypi) with API key auth.

Last verified 2 sources

Install

Generic

JSON
{
  "mcpServers": {
    "IBM watsonx.data MCP Server": {
      "command": "/path/from/which/command/ibm-watsonxdata-mcp-server",
      "args": ["--transport", "stdio"],
      "env": {
        "WATSONX_DATA_BASE_URL": "https://us-south.lakehouse.cloud.ibm.com/lakehouse/api",
        "WATSONX_DATA_API_KEY": "your_api_key_here",
        "WATSONX_DATA_INSTANCE_ID": "crn:v1:bluemix:public:lakehouse:us-south:a/..."
      }
    }
  }
}

Notes and caveats

  • Authenticates with an IBM Cloud IAM API key.
  • Supports read and write operations.
  • IBM also offers a hosted remote watsonx.data MCP server (see IBM Cloud watsonx.data remote querying docs) and a separate Document Library Retrieval MCP server.

More MCP servers for data and BI

Related reading

FAQ

What does the IBM watsonx.data MCP server do?

MCP server for IBM watsonx.data lakehouses with tools for instance status, Presto and Spark engines, catalog and schema exploration, SQL query execution, Spark applications and data ingestion.

How do I add the IBM watsonx.data MCP server to an MCP client?

IBM documents a Generic config; copy it from the Generic section of this page.

Does the IBM watsonx.data MCP server need authentication?

Yes, API key. Transport: stdio, Streamable HTTP. Status: Unlabelled, last checked October 17, 2026.

Sources

Last verified against 2 IBM pages, then re-checked independently.

Newsletter

New MCP servers, the week they ship

One email per week. New official MCP servers, the coding tools that support them and how developers wire them up.