Personal Reminder to myself. This is the updated link to KA958 article in Oracle support "Assistant: Download Reference for Oracle Database/GI Update, Revision, PSU, SPU(CPU), Bundle Patches, Patchsets and Base Releases"
This is the correct place to look for patches etc... for Oracle DB.
Oracle is investing heavily in AI and MCP. You can see many Open-source MCP GitHub projects here and the database MCP line of product here both for Oracle and MySql. There is a very useful MCP server for the OCI (Oracle Cloud Infrastructure) as well. What is MCP, and what implementations options are available for Oracle Database?
As organizations increasingly integrate AI into their workflows, one challenge keeps surfacing:
How do we securely and efficiently connect large language models (LLMs) to enterprise data in a standard fashion?
This is where MCP (Model Context Protocol) comes in.
Model Context Protocol (MCP) is an open standard that enables LLMs to securely access external systems such as databases, Mail servers, APIs, and files through a unified interface.
Think of MCP as a universal adapter for AI, eliminating the need to build custom integrations for every data source.
Images in this post were created with AI.
This post is a very enhanced version of previous, no longer correct one. In the AI world, few months change everything.
MCP is not just a technical convenience—it’s a shift in how we interact with data:
Oracle provides 4 primary ways to work with MCP, depending on your environment and your needs.
1. SQLcl MCP - A local client installation for personal use. It deploys Local MCP server using SQLcl.
2. Built-in ADB MCP - A specific Autonomous Database built in MCP connection. For simple and basic implementations.
3. OCI Database Tools MCP - Centrally managed OCI deployment, IAM roles, and governed SQL reports across cloud databases. For Cloud Database implementations on OCI or other cloud vendors.
4. ORDS MCP - ORDS Standalone deployments using direct user database connection pools, includes a /mcp endpoint for MCP Clients, also fully OAuth compliant to the MCP specification.
The first 2 options are mostly quick and easy personal or developer-oriented deployments. Options 3 & 4 are Enterprise oriented solutions. AFAIK all the MCP options here are free or free option of the Database.
|
Requirement |
Start with |
|
Developer / local experimentation |
SQLcl MCP |
|
Simple MCP access to Autonomous Database |
Built-in ADB MCP |
|
Centrally governed cloud deployment |
OCI Database Tools MCP |
|
Customer-managed enterprise MCP endpoint |
ORDS MCP |
Jeff Smith has a nice comparison table between SQLcl, OCI Database Tools and ORDS here. He has a brand-new video describing the 3 above mentioned options here.
Whatever you do, you might want to load Oracle Skills to your AI client, before you start. GitHub Oracle Skills.
Oracle SQLcl is a powerful, flexible, and free command-line interface designed for modern Oracle AI Database professionals.
SQLcl's integrated MCP Server bridges Oracle AI Databases with AI-driven solutions by allowing Large Language Models (LLMs) to interactively execute queries and process results. And should work with versions 19 and beyond. Connection credentials, wallets, and saved passwords remain local to SQLcl; however, SQL text and returned results may be passed to the LLM through the MCP client or terminal output.
The Oracle product page is here. The download page is here. This is a LiveLabs training about Exploring the SQLcl MCP server. And a short video by Jeff Smith about it.
The SQLcl MCP server exposes tools for common database tasks, including:
Most people use the SQLcl MCP that comes as part of the built in SQL Developer extension of VS Code (in that case no need for specific download).
The basic diagram is:
For historical reasons there is a built-in setup for Cline AI client in SQL Developer (see the blog post Using SQLcl in SQL Developer for VS Code for MCP with Cline if it's relevant to you).
I have a Codex extension in my VS Code. Wanted to connect to SQL Dev. connection named local_bi.
My Codex suggested 2 options for set up.
1. Add relevant section in config.toml that calls SQL Developer with relevant args. When I complained that it will force me to update the file with each version update of SQL Dev. It suggested option 2.
2. Install SQLcl in a stable folder and reference it in the config.toml (see the second image below)
After the setup everything worked fine with my 19.24 Oracle Database.
In my environment, I successfully connected to an Autonomous Database instance connection that was in my SQL Developer/SQLcl connection list. That is expected, the SQLcl MCP server just uses the connection in SQL Developer.
There is actually option 3, without MCP setup...
3. Direct SQLcl from Codex (no MCP)”. If Codex has terminal access and SQLcl is available locally, it can invoke SQLcl as a command-line program and use an existing named connection.
Codex → local terminal → SQLcl → saved named connection → Oracle DatabaseIn this model, SQLcl stores the saved connection and password locally (wallet). Codex does not need the password in its prompt or setup in config.toml.
This is useful when:
sql command;This route does not provide the standardized MCP tools such as list-connections, schema-information, or run-sql. Instead, Codex works through terminal commands and SQLcl output. It is therefore simpler to start, but less structured than the SQLcl MCP approach.
(Thanks, Efrat Landman for this part.)
If you want to read more about SQLcl MCP option, see here:
Controlled Oracle Actions with SQLcl MCP
Jeff Smith covers lots of relevant material:
Oracle Autonomous Database includes a built-in MCP server that can be enabled with a simple configuration. For real "Enterprise Solution", you should probably use "OCI Database Tools MCP", described in next section.
How to enable:
In OCI go to the ADB page and under Tags, add a free-form tag to your database:
Key: adb$feature
Value: {"name":"mcp_server","enable":true}
This approach is ideal for:
mcp-remote as a proxy. This was an environment-specific workaround rather than a requirement of the ADB MCP architecture.If you have problems with ADB MCP, here is a Troubleshooting Chapter.
Oracle Database Tools Service is a managed offering in Oracle Cloud Infrastructure (OCI) that enables you to create connections to any Oracle Database in OCI that can be reused by multiple users, resources, and services. Once a connection is established, use the web-based SQL Worksheet for direct SQL access or use the connection in a SQLcl session via the OCI Cloud Shell. Sensitive information such as passwords and Autonomous Database client credentials are stored securely and encrypted in your OCI vault and never viewed when connections are being used.
| Reporting Tools | - Publisher defines the queries; agent chooses report + parameters |
| Custom Tools - | Developer defines the operation; agent supplies parameters |
Built-in SQL Tools
LLM/agent generates SQL dynamically → maximum flexibility → governed primarily through the connected database user's privileges.
GenAI SQL Assistant
Natural language is translated through Oracle's GenAI/Select AI capabilities → Oracle Select AI participates in NL-to-SQL translation rather than leaving SQL generation solely to the external agent.
Reporting Tools
Human publishes approved SQL → agent selects the report and supplies parameters → strong governance for repeatable analytics.
Custom Tools
Developer exposes a specific database operation → agent invokes the operation with parameters → strongest contract for operational workflows.
|
Toolset |
MCP tool |
What it does |
Default roles |
|
Built-in SQL |
sql_run |
Runs SQL against the connected Oracle Database; results
are returned as CSV |
Operator, Administrator |
|
schema_information |
Examines/enriches metadata to provide detailed information
about a database schema |
User, Operator, Administrator |
|
|
request_status |
Polls an asynchronous request using its toolRequestId and
returns status/result |
User, Operator, Administrator |
|
|
Customizable Reporting |
report_list |
Lists the SQL Reports available to the user, including
IDs, descriptions and usage information |
User, Operator, Administrator |
|
report_execute |
Executes a SQL Report using its reportId and supplied
parameters; returns CSV |
User, Operator, Administrator |
|
|
report_sql |
Retrieves the underlying SQL for a SQL Report |
Operator |
|
|
Generative AI SQL Assistant |
dbtools_translate_natural _language_query_to_sql |
Converts a natural-language question into a validated
SQL statement |
User, Operator, Administrator |
|
Custom SQL |
administrator-defined name |
Runs an administrator-defined SQL or PL/SQL tool with
input parameters |
Operator |
Oracle REST Data Services (ORDS) MCP Server provides a secure, standards-based bridge between AI agents and Oracle AI Database. Through a remote streaming HTTPS /mcp endpoint, MCP-compatible clients can discover authorized database connections, inspect schema metadata, and execute SQL or PL/SQL using natural-language-driven workflows. ORDS MCP integrates with enterprise identity providers using OAuth 2.0/JWT authentication and restricts access to approved database resources, combining agentic AI capabilities with Oracle’s established security, governance, and auditing mechanisms.
If you intend to install ORDS MCP, please, please read ORDS: now a streaming HTTP MCP Server for Oracle Database before you do.
While ORDS MCP has rather modest tools list:
When connecting LLMs to databases, security is critical.
A recommended approach is to create a read-only MCP user with minimal privileges:
CREATE USER MCP_USER IDENTIFIED BY "<password>";
GRANT CREATE SESSION TO MCP_USER;
GRANT SELECT ON APP_SCHEMA.TABLE_1 TO MCP_USER;
GRANT SELECT ON APP_SCHEMA.TABLE_2 TO MCP_USER;
For easier management, you can use roles:
⚠️ Important: Always follow the principle of least privilege. LLMs generate actions based on intent, not risk awareness, so unrestricted access can lead to unintended operations.CREATE ROLE MCP_READ_ROLE;
GRANT SELECT ON APP_SCHEMA.TABLE_1 TO MCP_READ_ROLE;
GRANT MCP_READ_ROLE TO MCP_USER;
In my case I granted the MCP User full privileges in its schema and specific read only grants on other resources.
Oracle MCP provides native observability hooks:
DBTOOLS$MCP_LOG
SELECT * FROM V$SESSION WHERE PROGRAM = 'SQLcl-MCP';
This allows:
There isn't one “Oracle MCP.” There are several implementation models designed for different levels of control and various types of users.
SQLcl MCP provides a simple path for developers and local AI clients. Autonomous Database provides a native managed MCP endpoint. OCI Database Tools MCP adds centralized identity, governance, reporting, and controlled tools. ORDS MCP provides a customer-managed enterprise endpoint based on standard HTTP and OAuth.
With Oracle’s built-in support, you can enable secure, auditable, and AI-driven data access in minutes.
As AI adoption grows, MCP is quickly becoming a foundational component of modern data architectures.
There are 2 very different Generative AI based solutions for OAC (not for OAS, currently):
The OAC Governance Skill generates inventory and governance reports for an OAC instance.
OAC MCP server connects to OAC server and can run various tasks or run queries on OAC.
|
Capability |
Main
purpose |
Changes
OAC? |
Status |
|
Governance
Skill |
Inventory
and governance reporting |
Read-only
by default |
Community/demo |
|
OAC MCP
tools |
Search,
query, export and catalog administration |
Some
tools can modify content |
Oracle
Preview |
The major goal of the OAC Governance Reporting is to let you create Governance reports about the OAC server with AI tools (Codex/Claude/Cursor...).
Here you can find some explanations about OAC Governance Reporting, as well as the code itself (zip file) and a Guide: https://community.oracle.com/products/oracleanalytics/discussion/29242/oracle-analytics-governance-skill
Please note: "This content is intended for community knowledge sharing and demonstration purposes. It is not official Oracle documentation and should not be considered formal Oracle guidance or support documentation."
The main formats are Codex, Claude and General (for other options)
For connection with your OAC you will need the OAC server URL and the tokens.json file. The file is available from your OAC profile / Access Tokens menu.
Now I can work with my OAC server. Here I request to see all dataflows I have access to and sources/targets of specific dataflow:
The OAC MCP server does what any MCP tools should. It lets you interact directly from the AI tool (Codex/Claude/Cursor...) with the OAC server. It can run queries you want or do Administration of Catalog etc...
Always remember the MCP connection has its overhead. This very simple count distinct takes less than 1 second in OAC:
See here the full list of available tools. The MCP server has an impressive list of capabilities:
|
MCP Tool
Name |
Purpose |
|
oracle_analytics-search_catalog |
Search catalog objects such as workbooks,
folders, datasets, connections, subject areas, analyses, reports, dashboards,
and scripts. |
|
oracle_analytics-find_matching_datasources |
Match a natural-language question to relevant OAC
data sources. |
|
oracle_analytics-describe_data |
Retrieve table and column metadata for subject
areas or datasets. |
|
oracle_analytics-execute_logical_sql |
Execute Oracle Analytics Logical SQL and return
query results. |
|
oracle_analytics-save_catalog_content |
Create or replace workbook or connection catalog
content |
|
oracle_analytics-export_workbook |
Export a workbook to PNG or PDF. |
|
oracle_analytics-create_catalog_folder |
Create a catalog folder. |
|
oracle_analytics-copy_catalog_item |
Copy a catalog item. |
|
oracle_analytics-move_catalog_item |
Move a catalog item. |
|
oracle_analytics-delete_catalog_item |
Delete a catalog item. |
|
oracle_analytics-update_catalog_acl |
Update catalog permissions. |
to create the connection, we need the MCP Connect option from the Profile:
The OAC MCP Server documentation is here in the Developers Guide
There are Blogs and Videos about it as well.
Mike Durran provides a 55-minute presentation about OAC MCP here as well.
When I did the setups, I didn't bother with both setups and just asked my Codex to do the setup for both (MCP and Governance). I provided Codex with the relevant documentation links and required files, and it configured both capabilities within a few minutes.
For anyone who prefers a manual installation, I asked Codex to summarize the steps it performed: