Oracle adds MCP support to two of its flagship tools, SQLcl and
SQL Developer for VS Code, in an attempt to simplify user interaction with the database.

SQLcl is of course the standard command line interface for the Oracle database. It now becomes a MCP server as well.
That way it facilitates AI tools and coding assistants to securely connect and interact with Oracle databases using natural language to execute tasks ranging from generating SQL to creating complex applications.

The available MCP tools it offers are:

List Connections: This tool allows the LLM to browse a list of defined Oracle database connections that users have saved in SQLcl or the SQL Developer extension for VS Code. For example, a user can ask the LLM to "show me what databases are available," and it will list the names of the saved connections.

Run SQL: This is a generic, wide-open tool that enables the LLM to execute SQL statements on an established database connection. It can also handle PL/SQL.

Run SQLcl: Used to run any SQLcl command

Disconnect/Close Connection: A tool to terminate the database connection once operations are complete.

SQL Developer is of course the GUI defacto query, development, and administration tool for Oracle Database professionals, which integrated with VS Code makes managing the entire development cycle effortless; execute SQL queries and scripts, perform PL/SQL development, and interact with your database schema objects within VS Code. The newest update of the SQL developer extension for VS Code automatically registers the SQLcl MCP server for Copilot making its tools immediately available.

With MCP, Oracle is trying to simplify the interaction with the database both for developers and business users alike. Devs can now ask questions instead of writing SQL, such as "create me a table with vector search", while business users can do reporting by for instance ask for "what were the most popular shoes being sold leading up to the Boston Marathon?". The queries can even be refined like "what about the ones that were sold only in New Hampshire?"; the AI would iteratively adjust the data retrieval and presentation based on these natural language prompts.

Oracle intends to release more MCP tools like in data guarding, which for instance will assist with managing high availability, disaster recovery, switchovers, and failovers through natural language commands. An example query would be to ask about "what is my high availability disaster recovery situation?".

With tooling like that, Oracle follows in the footsteps of other RDBMS' who have already embraced the new Agentic AI trend. It's something that we've explored in "Agentic AI For PostgreSQL" where Crystal DBA's Postgres MCP Pro server added new and exciting capabilities:

• Check Database Health - analyze index health, connection utilization, buffer cache, vacuum health, sequence limits, replication lag, and more.
  
  
• Index Tune - explore thousands of possible indexes to find the best solution for your workload, using industrial-strength algorithms.
  
  
• Check Query Plans - validate and optimize performance by reviewing EXPLAIN plans and simulating the impact of hypothetical indexes.
  
  
• Utilize️ Schema Intelligence - context-aware SQL generation based on detailed understanding of the database schema.
  
  
• Utilize️ Safe SQL Execution - configurable access control, including support for read-only mode and safe SQL parsing, making it usable for both development and production.

At the end of the day, MCP has overnight changed the way we interact with our tools. Now it targets the Database too.

More Information

Introducing MCP Server for Oracle Database

Related Articles

Agentic AI For PostgreSQL

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info