9 Get Started with Oracle Analytics Cloud MCP Tools (Preview)
The July 2026 Oracle Analytics Cloud release is based on MCP Protocol 2025-06-18.
This chapter explains the Oracle Analytics Cloud MCP tools and helps you start using them. It describes how to connect MCP clients to Oracle Analytics Cloud, introduces the available tools, explains the MCP request and session model, and provides recommended workflows, best practices, and troubleshooting information for working safely and effectively with OAC MCP tools.
The information in this guide is intended for users who want to discover catalog assets, inspect data models, run Logical SQL, create or update catalog content, export workbooks, and manage catalog items through JSON-RPC MCP calls.
Caution:
Oracle Analytics provides a Model Context Protocol (MCP) server that allows AI clients direct access and interaction with Oracle Analytics data and functionality. This introduces security risks since you might inadvertently expose unintended data.
The Oracle Analytics MCP tools are authenticated with an OAuth 2.0 access token and run with the same permissions as the user who obtains the access token. Ensure that any users who use the MCP server only have access to data that can be shared with LLMs.
MCP is a new protocol and a dynamic area that is constantly improving. While the Oracle Analytics Cloud endpoints are supported and available for use in your projects, there may be some changes as Oracle improves this area. When using the MCP server in your agents and AI applications, Oracle recommends implementing evaluations and observability to ensure reliability.
Topics: